Based on the latest models from Hugging Face.
| Model ID | Task | Est. Min RAM | Downloads |
|---|---|---|---|
| sentence-transformers/all-MiniLM-L6-v2 | sentence-similarity | 8GB (Est.) * | 202,457,760 |
| google-bert/bert-base-uncased | fill-mask | 8GB (Est.) * | 61,107,059 |
| Qwen/Qwen3-VL-2B-Instruct | image-text-to-text | 4GB - 8GB | 51,737,575 |
| google/electra-base-discriminator | General | 8GB (Est.) * | 47,456,524 |
| Falconsai/nsfw_image_detection | image-classification | 8GB (Est.) * | 36,569,210 |
| sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 | sentence-similarity | 8GB (Est.) * | 33,806,026 |
| cross-encoder/ms-marco-MiniLM-L6-v2 | text-ranking | 8GB (Est.) * | 23,161,908 |
| BAAI/bge-small-en-v1.5 | feature-extraction | 2GB - 4GB | 21,059,459 |
| openai/clip-vit-base-patch32 | zero-shot-image-classification | 8GB (Est.) * | 20,265,013 |
| openai/clip-vit-large-patch14-336 | zero-shot-image-classification | 8GB (Est.) * | 18,842,802 |
| amazon/chronos-2 | time-series-forecasting | 8GB (Est.) * | 16,871,423 |
| BAAI/bge-m3 | sentence-similarity | 8GB (Est.) * | 16,315,813 |
| Qwen/Qwen3-0.6B | text-generation | 8GB - 16GB | 15,869,433 |
| colbert-ir/colbertv2.0 | General | 8GB (Est.) * | 15,507,418 |
| openai-community/gpt2 | text-generation | 8GB (Est.) * | 13,939,545 |
| Qwen/Qwen2.5-7B-Instruct | text-generation | 8GB - 16GB | 12,478,456 |
| Qwen/Qwen2.5-1.5B-Instruct | text-generation | 8GB - 16GB | 10,575,525 |
| pyannote/segmentation-3.0 | voice-activity-detection | 8GB (Est.) * | 10,451,403 |
| Qwen/Qwen2.5-3B-Instruct | text-generation | 4GB - 8GB | 10,327,414 |
| deepseek-ai/DeepSeek-V3.2 | text-generation | 8GB (Est.) * | 10,281,288 |
| pyannote/speaker-diarization-3.1 | automatic-speech-recognition | 8GB (Est.) * | 10,236,804 |
| Qwen/Qwen3-4B-Instruct-2507 | text-generation | 8GB - 16GB | 9,690,832 |
| hexgrad/Kokoro-82M | text-to-speech | 8GB (Est.) * | 9,684,840 |
| meta-llama/Llama-3.1-8B-Instruct | text-generation | 8GB - 16GB | 9,258,938 |
| Qwen/Qwen3-8B | text-generation | 8GB - 16GB | 8,677,900 |
| Qwen/Qwen2.5-VL-7B-Instruct | image-text-to-text | 8GB - 16GB | 8,012,730 |
| Qwen/Qwen3-4B | text-generation | 8GB - 16GB | 7,458,685 |
| BAAI/bge-reranker-v2-m3 | text-classification | 8GB (Est.) * | 7,357,778 |
| zai-org/GLM-OCR | image-to-text | 8GB (Est.) * | 7,198,085 |
| coqui/XTTS-v2 | text-to-speech | 8GB (Est.) * | 6,734,583 |
| Kijai/WanVideo_comfy | General | 8GB (Est.) * | 6,644,844 |
| openai/whisper-large-v3-turbo | automatic-speech-recognition | 8GB (Est.) * | 6,628,980 |
| openai/gpt-oss-20b | text-generation | 32GB - 48GB | 6,403,555 |
| Qwen/Qwen3.5-9B | image-text-to-text | 8GB - 16GB | 6,378,899 |
| Comfy-Org/Wan_2.2_ComfyUI_Repackaged | General | 8GB (Est.) * | 6,109,619 |
| intfloat/multilingual-e5-large | feature-extraction | 2GB - 4GB | 6,069,011 |
| Qwen/Qwen3-Embedding-0.6B | feature-extraction | 8GB - 16GB | 6,051,527 |
| Qwen/Qwen2.5-0.5B-Instruct | text-generation | 8GB - 16GB | 5,733,042 |
| moonshotai/Kimi-K2.5 | image-text-to-text | 8GB (Est.) * | 5,219,582 |
| openai/whisper-large-v3 | automatic-speech-recognition | 8GB (Est.) * | 4,857,074 |
| ProsusAI/finbert | text-classification | 8GB (Est.) * | 4,677,698 |
| meta-llama/Llama-3.2-1B-Instruct | text-generation | 4GB - 8GB | 4,608,974 |
| answerdotai/ModernBERT-base | fill-mask | 8GB (Est.) * | 4,387,008 |
| mixedbread-ai/mxbai-embed-large-v1 | feature-extraction | 2GB - 4GB | 4,285,392 |
| meta-llama/Llama-3.2-3B-Instruct | text-generation | 4GB - 8GB | 4,282,006 |
| google/gemma-4-31B-it | image-text-to-text | 32GB - 48GB | 4,003,761 |
| deepseek-ai/DeepSeek-R1 | text-generation | 8GB (Est.) * | 3,969,336 |
| Qwen/Qwen3.5-35B-A3B | image-text-to-text | 32GB - 48GB | 3,892,029 |
| Qwen/Qwen3-VL-8B-Instruct | image-text-to-text | 8GB - 16GB | 3,812,138 |
| openai/gpt-oss-120b | text-generation | 64GB+ | 3,492,717 |
| meta-llama/Meta-Llama-3-8B | text-generation | 8GB - 16GB | 3,295,899 |
| Qwen/Qwen3.5-27B | image-text-to-text | 32GB - 48GB | 3,240,204 |
| Qwen/Qwen3.5-4B | image-text-to-text | 8GB - 16GB | 3,016,647 |
| Qwen/Qwen3-14B | text-generation | 32GB - 48GB | 2,943,352 |
| google/gemma-4-26B-A4B-it | image-text-to-text | 32GB - 48GB | 2,935,876 |
| Qwen/Qwen3.5-0.8B | image-text-to-text | 8GB - 16GB | 2,703,683 |
| Comfy-Org/z_image_turbo | General | 8GB (Est.) * | 2,634,144 |
| unsloth/gemma-4-26B-A4B-it-GGUF | image-text-to-text | 32GB - 48GB | 2,364,587 |
| Qwen/Qwen3-32B | text-generation | 32GB - 48GB | 2,359,840 |
| mistralai/Mistral-7B-Instruct-v0.3 | General | 8GB - 16GB | 2,334,291 |
| Qwen/Qwen3-Coder-30B-A3B-Instruct | text-generation | 32GB - 48GB | 2,296,762 |
| google/gemma-4-E4B-it | any-to-any | 8GB - 16GB | 2,264,052 |
| apple/mobilevit-small | image-classification | 8GB (Est.) * | 2,239,694 |
| facebook/sam3 | mask-generation | 8GB (Est.) * | 2,181,006 |
| Alibaba-NLP/gte-multilingual-base | sentence-similarity | 8GB (Est.) * | 2,179,526 |
| mistralai/Mistral-7B-Instruct-v0.2 | text-generation | 8GB - 16GB | 2,072,829 |
| pyannote/speaker-diarization-community-1 | automatic-speech-recognition | 8GB (Est.) * | 2,071,870 |
| Qwen/Qwen3-VL-4B-Instruct | image-text-to-text | 8GB - 16GB | 2,071,235 |
| deepseek-ai/DeepSeek-OCR | image-text-to-text | 8GB (Est.) * | 2,045,995 |
| stabilityai/stable-diffusion-xl-base-1.0 | text-to-image | 8GB - 12GB | 1,983,612 |
| facebook/bart-large-cnn | summarization | 8GB (Est.) * | 1,897,550 |
| Qwen/Qwen3-Embedding-8B | feature-extraction | 8GB - 16GB | 1,851,216 |
| google/gemma-3-4b-it | image-text-to-text | 8GB - 16GB | 1,821,245 |
| Qwen/Qwen3-Embedding-4B | feature-extraction | 8GB - 16GB | 1,821,114 |
| Qwen/Qwen2.5-Coder-7B-Instruct | text-generation | 8GB - 16GB | 1,799,539 |
| Qwen/Qwen3.5-35B-A3B-FP8 | image-text-to-text | 32GB - 48GB | 1,795,013 |
| Qwen/Qwen3-VL-Embedding-2B | sentence-similarity | 4GB - 8GB | 1,723,170 |
| Qwen/Qwen3-ASR-1.7B | automatic-speech-recognition | 8GB - 16GB | 1,715,272 |
| google/gemma-4-E2B-it | any-to-any | 4GB - 8GB | 1,709,540 |
| Lightricks/LTX-2.3 | image-to-video | 8GB (Est.) * | 1,705,763 |
| ResembleAI/chatterbox | text-to-speech | 8GB (Est.) * | 1,662,832 |
| Qwen/Qwen2.5-0.5B | text-generation | 8GB - 16GB | 1,607,804 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 | text-generation | 32GB - 48GB | 1,530,599 |
| Qwen/Qwen3-TTS-12Hz-1.7B-CustomVoice | text-to-speech | 8GB - 16GB | 1,528,493 |
| stable-diffusion-v1-5/stable-diffusion-v1-5 | text-to-image | 8GB - 12GB | 1,516,480 |
| unsloth/gemma-4-31B-it-GGUF | image-text-to-text | 32GB - 48GB | 1,513,530 |
| black-forest-labs/FLUX.2-klein-base-4B | image-to-image | 8GB - 16GB | 1,497,540 |
| Qwen/Qwen3.5-2B | image-text-to-text | 4GB - 8GB | 1,496,578 |
| meta-llama/Llama-3.1-8B | text-generation | 8GB - 16GB | 1,456,797 |
| lightx2v/Wan2.2-Distill-Loras | image-to-video | 8GB (Est.) * | 1,450,065 |
| Qwen/Qwen3-TTS-12Hz-1.7B-Base | General | 8GB - 16GB | 1,433,577 |
| Qwen/Qwen3-Reranker-0.6B | text-ranking | 8GB - 16GB | 1,424,638 |
| unsloth/gemma-4-E4B-it-GGUF | image-text-to-text | 8GB - 16GB | 1,380,188 |
| deepseek-ai/DeepSeek-OCR-2 | image-text-to-text | 8GB (Est.) * | 1,351,813 |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 | text-generation | 64GB+ | 1,342,118 |
| Qwen/Qwen3-30B-A3B | text-generation | 32GB - 48GB | 1,341,418 |
| meta-llama/Meta-Llama-3-8B-Instruct | text-generation | 8GB - 16GB | 1,337,083 |
| microsoft/Phi-4-mini-instruct | text-generation | 8GB (Est.) * | 1,302,910 |
| meta-llama/Llama-3.2-1B | text-generation | 4GB - 8GB | 1,296,907 |
| docling-project/docling-models | General | 8GB (Est.) * | 1,285,001 |
| nvidia/Gemma-4-31B-IT-NVFP4 | text-generation | 32GB - 48GB | 1,267,606 |
| HauhauCS/Qwen3.5-35B-A3B-Uncensored-HauhauCS-Aggressive | image-text-to-text | 32GB - 48GB | 1,267,203 |
| Qwen/Qwen2.5-7B | text-generation | 8GB - 16GB | 1,251,082 |
| Tongyi-MAI/Z-Image-Turbo | text-to-image | 8GB - 12GB | 1,171,419 |
| facebook/nllb-200-distilled-600M | translation | 8GB (Est.) * | 1,160,781 |
| microsoft/VibeVoice-Realtime-0.5B | text-to-speech | 8GB - 16GB | 1,155,529 |
| unsloth/Qwen3.5-35B-A3B-GGUF | image-text-to-text | 32GB - 48GB | 1,150,016 |
| Qwen/Qwen3.5-397B-A17B-FP8 | image-text-to-text | 64GB+ | 1,106,176 |
| Kijai/LTX2.3_comfy | General | 8GB (Est.) * | 1,094,311 |
| HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive | General | 8GB - 16GB | 1,051,872 |
| k2-fsa/OmniVoice | text-to-speech | 8GB (Est.) * | 1,019,685 |
| meta-llama/Llama-3.2-3B | text-generation | 4GB - 8GB | 1,014,421 |
| google/embeddinggemma-300m | sentence-similarity | 8GB (Est.) * | 945,151 |
| MiniMaxAI/MiniMax-M2.5 | text-generation | 8GB (Est.) * | 919,001 |
| Qwen/Qwen3.5-122B-A10B | image-text-to-text | 64GB+ | 909,381 |
| mistralai/Mistral-7B-v0.1 | text-generation | 8GB - 16GB | 909,000 |
| Qwen/Qwen3.5-27B-FP8 | image-text-to-text | 32GB - 48GB | 902,476 |
| mistralai/Voxtral-Mini-4B-Realtime-2602 | automatic-speech-recognition | 8GB - 16GB | 895,486 |
| deepseek-ai/DeepSeek-V3 | text-generation | 8GB (Est.) * | 892,696 |
| stabilityai/sdxl-turbo | text-to-image | 8GB - 12GB | 874,445 |
| unsloth/Qwen3.5-9B-GGUF | image-text-to-text | 8GB - 16GB | 852,425 |
| HuggingFaceTB/SmolLM2-135M-Instruct | text-generation | 8GB (Est.) * | 824,432 |
| Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-GGUF | image-text-to-text | 32GB - 48GB | 809,903 |
| lmstudio-community/gemma-4-E4B-it-GGUF | General | 8GB - 16GB | 789,280 |
| Lightricks/LTX-2 | image-to-video | 8GB (Est.) * | 773,133 |
| Qwen/Qwen3-Reranker-4B | text-ranking | 8GB - 16GB | 760,826 |
| lightonai/LightOnOCR-2-1B | image-text-to-text | 4GB - 8GB | 760,044 |
| NeoQuasar/Kronos-Tokenizer-base | time-series-forecasting | 8GB (Est.) * | 758,237 |
| Systran/faster-whisper-large-v3 | automatic-speech-recognition | 8GB (Est.) * | 750,302 |
| HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive | image-text-to-text | 8GB - 16GB | 739,022 |
| Qwen/Qwen3-VL-Embedding-8B | sentence-similarity | 8GB - 16GB | 737,174 |
| black-forest-labs/FLUX.1-schnell | text-to-image | 8GB - 12GB | 731,975 |
| microsoft/VibeVoice-ASR | automatic-speech-recognition | 8GB (Est.) * | 728,117 |
| unsloth/gemma-4-E2B-it-GGUF | image-text-to-text | 4GB - 8GB | 720,162 |
| ZhengPeng7/BiRefNet | image-segmentation | 8GB (Est.) * | 718,179 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8 | text-generation | 32GB - 48GB | 715,180 |
| Qwen/Qwen3.5-397B-A17B | image-text-to-text | 64GB+ | 704,846 |
| facebook/dinov3-vitl16-pretrain-lvd1689m | image-feature-extraction | 2GB - 4GB | 700,214 |
| Qwen/Qwen3-TTS-12Hz-0.6B-Base | text-to-speech | 8GB - 16GB | 697,436 |
| black-forest-labs/FLUX.1-dev | text-to-image | 8GB - 12GB | 697,280 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B | text-generation | 8GB - 16GB | 672,769 |
| Qwen/Qwen3.5-35B-A3B-GPTQ-Int4 | image-text-to-text | 32GB - 48GB | 672,735 |
| Lightricks/LTX-2.3-fp8 | image-to-video | 8GB (Est.) * | 672,510 |
| google/gemma-3-1b-it | text-generation | 4GB - 8GB | 665,582 |
| unsloth/Qwen3.6-35B-A3B-GGUF | image-text-to-text | 32GB - 48GB | 662,293 |
| unsloth/Qwen3.5-27B-GGUF | image-text-to-text | 32GB - 48GB | 655,842 |
| unsloth/Qwen3.5-4B-GGUF | image-text-to-text | 8GB - 16GB | 647,061 |
| Qwen/Qwen3-Coder-Next | text-generation | 8GB (Est.) * | 638,721 |
| Qwen/Qwen3.5-122B-A10B-FP8 | image-text-to-text | 64GB+ | 634,977 |
| nanonets/Nanonets-OCR2-3B | image-text-to-text | 4GB - 8GB | 616,470 |
| Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-GGUF | image-text-to-image | 8GB - 16GB | 612,939 |
| mistralai/Mixtral-8x7B-Instruct-v0.1 | General | 8GB - 16GB | 602,710 |
| mlx-community/gpt-oss-20b-MXFP4-Q8 | text-generation | 32GB - 48GB | 601,730 |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-FP8 | text-generation | 64GB+ | 597,169 |
| cyankiwi/gemma-4-26B-A4B-it-AWQ-4bit | image-text-to-text | 32GB - 48GB | 580,678 |
| nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 | text-generation | 64GB+ | 577,263 |
| Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled | image-text-to-text | 32GB - 48GB | 572,828 |
| nvidia/Qwen3.5-397B-A17B-NVFP4 | text-generation | 64GB+ | 558,093 |
| Lightricks/LTX-Video | image-to-video | 8GB (Est.) * | 552,547 |
| microsoft/Florence-2-base | image-text-to-text | 8GB (Est.) * | 545,630 |
| nvidia/personaplex-7b-v1 | audio-to-audio | 8GB - 16GB | 522,681 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | text-generation | 32GB - 48GB | 511,416 |
| meta-llama/Llama-3.3-70B-Instruct | text-generation | 64GB+ | 494,422 |
| zai-org/GLM-5 | text-generation | 8GB (Est.) * | 484,607 |
| nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 | text-generation | 32GB - 48GB | 477,860 |
| Qwen/Qwen2.5-Omni-7B | any-to-any | 8GB - 16GB | 450,922 |
| HuggingFaceTB/SmolLM3-3B | text-generation | 4GB - 8GB | 445,428 |
| Qwen/Qwen3-ASR-0.6B | automatic-speech-recognition | 8GB - 16GB | 437,226 |
| meta-llama/Llama-2-7b-chat-hf | text-generation | 8GB - 16GB | 423,519 |
| Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2 | image-text-to-text | 32GB - 48GB | 419,048 |
| Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF | image-text-to-text | 32GB - 48GB | 414,824 |
| HauhauCS/Qwen3.5-27B-Uncensored-HauhauCS-Aggressive | General | 32GB - 48GB | 411,226 |
| codgician/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GPTQ-int4 | image-text-to-text | 32GB - 48GB | 398,716 |
| cyankiwi/gemma-4-31B-it-AWQ-4bit | image-text-to-text | 32GB - 48GB | 392,883 |
| nvidia/parakeet-tdt-0.6b-v3 | automatic-speech-recognition | 8GB - 16GB | 391,544 |
| Systran/faster-whisper-small | automatic-speech-recognition | 8GB (Est.) * | 388,240 |
| PaddlePaddle/PaddleOCR-VL-1.5 | image-text-to-text | 8GB (Est.) * | 387,123 |
| Qwen/Qwen3-Omni-30B-A3B-Instruct | any-to-any | 32GB - 48GB | 383,407 |
| QuantTrio/Qwen3.5-27B-AWQ | image-text-to-text | 32GB - 48GB | 383,325 |
| LiquidAI/LFM2.5-1.2B-Instruct | text-generation | 4GB - 8GB | 382,551 |
| Comfy-Org/ace_step_1.5_ComfyUI_files | General | 8GB (Est.) * | 379,287 |
| briaai/RMBG-2.0 | image-segmentation | 8GB (Est.) * | 377,160 |
| unsloth/Qwen3.5-122B-A10B-GGUF | image-text-to-text | 64GB+ | 365,240 |
| google/gemma-2-2b-it | text-generation | 4GB - 8GB | 358,646 |
| NeoQuasar/Kronos-base | time-series-forecasting | 8GB (Est.) * | 343,352 |
| yuvalkirstain/PickScore_v1 | zero-shot-image-classification | 8GB (Est.) * | 328,467 |
| circlestone-labs/Anima | General | 8GB (Est.) * | 328,138 |
| jinaai/jina-embeddings-v4 | visual-document-retrieval | 8GB (Est.) * | 327,431 |
| microsoft/VibeVoice-ASR-HF | audio-text-to-text | 4GB - 8GB | 322,347 |
| unsloth/Qwen3.5-2B-GGUF | image-text-to-text | 4GB - 8GB | 322,002 |
| nvidia/Nemotron-Cascade-2-30B-A3B | text-generation | 32GB - 48GB | 316,925 |
| google/gemma-4-31B | image-text-to-text | 32GB - 48GB | 308,566 |
| Qwen/Qwen3-Next-80B-A3B-Instruct | text-generation | 64GB+ | 303,849 |
| deepseek-ai/DeepSeek-R1-0528-Qwen3-8B | text-generation | 8GB - 16GB | 302,318 |
| zai-org/GLM-5.1-FP8 | text-generation | 8GB (Est.) * | 297,138 |
| ggml-org/gemma-4-26B-A4B-it-GGUF | General | 32GB - 48GB | 297,053 |
| Qwen/Qwen3.5-122B-A10B-GPTQ-Int4 | image-text-to-text | 64GB+ | 295,940 |
| mistralai/Devstral-Small-2-24B-Instruct-2512 | General | 32GB - 48GB | 290,465 |
| Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF | text-generation | 8GB - 16GB | 289,992 |
| MiniMaxAI/MiniMax-M2.7 | text-generation | 8GB (Est.) * | 288,848 |
| unsloth/Qwen3.5-0.8B-GGUF | image-text-to-text | 8GB - 16GB | 287,799 |
| Qwen/Qwen3.5-27B-GPTQ-Int4 | image-text-to-text | 32GB - 48GB | 276,512 |
| Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8 | text-generation | 32GB - 48GB | 273,327 |
| unsloth/LTX-2.3-GGUF | image-to-video | 8GB (Est.) * | 273,056 |
| Nanbeige/Nanbeige4.1-3B | text-generation | 4GB - 8GB | 272,436 |
| Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF | image-text-to-text | 8GB - 16GB | 271,044 |
| allenai/olmOCR-2-7B-1025-FP8 | image-text-to-text | 8GB - 16GB | 270,340 |
| cagliostrolab/animagine-xl-4.0 | text-to-image | 8GB - 12GB | 267,953 |
| bartowski/google_gemma-4-31B-it-GGUF | image-text-to-text | 32GB - 48GB | 267,135 |
| stabilityai/stable-video-diffusion-img2vid-xt | image-to-video | 8GB (Est.) * | 257,759 |
| Qwen/Qwen3-ForcedAligner-0.6B | automatic-speech-recognition | 8GB - 16GB | 257,751 |
| MoritzLaurer/mDeBERTa-v3-base-mnli-xnli | zero-shot-classification | 8GB (Est.) * | 254,085 |
| kpsss34/FHDR_Uncensored | text-to-image | 8GB - 12GB | 248,892 |
| facebook/fasttext-language-identification | text-classification | 8GB (Est.) * | 248,067 |
| Jackrong/Qwopus3.5-9B-v3 | image-text-to-text | 8GB - 16GB | 247,709 |
| mradermacher/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-i1-GGUF | General | 32GB - 48GB | 245,784 |
| unsloth/gpt-oss-20b-GGUF | text-generation | 32GB - 48GB | 244,520 |
| HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive | General | 8GB - 16GB | 243,400 |
| bartowski/Meta-Llama-3.1-8B-Instruct-GGUF | text-generation | 8GB - 16GB | 241,629 |
| CohereLabs/cohere-transcribe-03-2026 | automatic-speech-recognition | 8GB (Est.) * | 241,323 |
| black-forest-labs/FLUX.2-klein-4B | image-to-image | 8GB - 16GB | 239,305 |
| Qwen/Qwen3-VL-Reranker-2B | text-ranking | 4GB - 8GB | 235,832 |
| HauhauCS/Gemma-4-E2B-Uncensored-HauhauCS-Aggressive | image-text-to-text | 4GB - 8GB | 234,620 |
| black-forest-labs/FLUX.1-Fill-dev | General | 8GB (Est.) * | 229,623 |
| bartowski/google_gemma-4-26B-A4B-it-GGUF | image-text-to-text | 32GB - 48GB | 225,849 |
| facebook/detr-resnet-50 | object-detection | 8GB (Est.) * | 222,363 |
| jinaai/jina-embeddings-v5-text-small | feature-extraction | 2GB - 4GB | 221,191 |
| unsloth/Qwen3-Coder-Next-GGUF | text-generation | 8GB (Est.) * | 216,151 |
| mlx-community/gemma-4-e2b-it-4bit | any-to-any | 4GB - 8GB | 213,094 |
| Qwen/Qwen-Image | text-to-image | 8GB - 12GB | 210,650 |
| Qwen/Qwen3.6-35B-A3B | image-text-to-text | 32GB - 48GB | 209,112 |
| black-forest-labs/FLUX.2-dev | image-to-image | 8GB (Est.) * | 203,914 |
| google/medgemma-27b-it | image-text-to-text | 32GB - 48GB | 200,285 |
| lightx2v/Qwen-Image-Edit-2511-Lightning | image-to-image | 8GB (Est.) * | 197,801 |
| cyankiwi/Qwen3.5-27B-AWQ-4bit | image-text-to-text | 32GB - 48GB | 196,243 |
| unsloth/gpt-oss-120b-GGUF | text-generation | 64GB+ | 195,365 |
| baidu/Qianfan-OCR | image-text-to-text | 8GB (Est.) * | 194,368 |
| mudler/gemma-4-26B-A4B-it-APEX-GGUF | General | 32GB - 48GB | 191,076 |
| deepseek-ai/DeepSeek-V3.2-Exp | text-generation | 8GB (Est.) * | 185,963 |
| google/timesfm-2.5-200m-transformers | time-series-forecasting | 8GB (Est.) * | 184,123 |
| google/medgemma-4b-it | image-text-to-text | 8GB - 16GB | 183,361 |
| HauhauCS/Qwen3.5-122B-A10B-Uncensored-HauhauCS-Aggressive | image-text-to-text | 64GB+ | 182,015 |
| QuantStack/Wan2.2-I2V-A14B-GGUF | image-to-video | 32GB - 48GB | 181,524 |
| bartowski/google_gemma-4-E4B-it-GGUF | image-text-to-text | 8GB - 16GB | 180,943 |
| bineric/lynx-instruct-30b | text-generation | 32GB - 48GB | 180,538 |
| douyamv/Gemma-4-31B-JANG_4M-CRACK-GGUF | text-generation | 32GB - 48GB | 176,351 |
| HauhauCS/Qwen3.6-35B-A3B-Uncensored-HauhauCS-Aggressive | image-text-to-text | 32GB - 48GB | 173,454 |
| nvidia/parakeet-tdt-0.6b-v2 | automatic-speech-recognition | 8GB - 16GB | 170,800 |
| Qwen/Qwen-Image-Edit-2511 | image-to-image | 8GB (Est.) * | 170,080 |
| BioMistral/BioMistral-7B | text-generation | 8GB - 16GB | 167,255 |
| Jackrong/Qwopus3.5-27B-v3-GGUF | image-text-to-text | 32GB - 48GB | 166,271 |
| cyankiwi/Qwen3.5-9B-AWQ-4bit | image-text-to-text | 8GB - 16GB | 166,211 |
| deepseek-ai/DeepSeek-R1-Distill-Llama-70B | text-generation | 64GB+ | 163,943 |
| Comfy-Org/z_image | General | 8GB (Est.) * | 163,703 |
| huihui-ai/Huihui-Qwen3.5-35B-A3B-Claude-4.6-Opus-abliterated | image-text-to-text | 32GB - 48GB | 162,975 |
| mistralai/Ministral-3-3B-Instruct-2512 | General | 4GB - 8GB | 162,372 |
| ggml-org/gemma-4-E4B-it-GGUF | General | 8GB - 16GB | 162,347 |
| apolo13x/Qwen3.5-27B-NVFP4 | image-text-to-text | 32GB - 48GB | 160,947 |
| Qwen/Qwen3.6-35B-A3B-FP8 | image-text-to-text | 32GB - 48GB | 160,890 |
| dealignai/Gemma-4-31B-JANG_4M-CRACK | image-text-to-text | 32GB - 48GB | 160,417 |
| google/gemma-4-E4B | any-to-any | 8GB - 16GB | 159,586 |
| nphSi/Z-Image-Lora | text-to-image | 8GB - 12GB | 158,938 |
| Comfy-Org/stable-diffusion-v1-5-archive | General | 8GB (Est.) * | 150,980 |
| nvidia/GLM-5-NVFP4 | text-generation | 8GB (Est.) * | 150,083 |
| unsloth/Qwen3-Coder-30B-A3B-Instruct-GGUF | text-generation | 32GB - 48GB | 149,330 |
| mudler/Qwen3.5-35B-A3B-APEX-GGUF | text-generation | 32GB - 48GB | 148,298 |
| stepfun-ai/Step-3.5-Flash | text-generation | 8GB (Est.) * | 147,233 |
| Jackrong/Qwopus3.5-9B-v3-GGUF | image-text-to-text | 8GB - 16GB | 142,962 |
| paperscarecrow/Gemma-4-31B-it-abliterated | General | 32GB - 48GB | 142,737 |
| facebook/tribev2 | General | 8GB (Est.) * | 141,742 |
| darkc0de/XORTRON.CriminalComputing.LARGE.2026.3 | text-generation | 8GB (Est.) * | 139,882 |
| prithivMLmods/Common-Voice-Gender-Detection | audio-classification | 4GB - 8GB | 139,362 |
| lmstudio-community/Qwen3.6-35B-A3B-GGUF | General | 32GB - 48GB | 138,914 |
| city96/FLUX.1-dev-gguf | text-to-image | 8GB - 12GB | 133,474 |
| microsoft/VibeVoice-1.5B | text-to-speech | 8GB - 16GB | 133,000 |
| LilaRest/gemma-4-31B-it-NVFP4-turbo | text-generation | 32GB - 48GB | 132,415 |
| google/gemma-4-E2B | any-to-any | 4GB - 8GB | 131,513 |
| fastino/gliner2-multi-v1 | General | 8GB (Est.) * | 129,166 |
| lrzjason/Anything2Real | image-to-image | 8GB (Est.) * | 126,442 |
| stabilityai/stable-diffusion-3.5-medium | text-to-image | 8GB - 12GB | 125,724 |
| FunAudioLLM/Fun-CosyVoice3-0.5B-2512 | text-to-speech | 8GB - 16GB | 125,702 |
| LiquidAI/LFM2.5-VL-1.6B | image-text-to-text | 8GB - 16GB | 123,770 |
| datalab-to/chandra-ocr-2 | image-text-to-text | 8GB (Est.) * | 122,947 |
| TeichAI/gemma-4-31B-it-Claude-Opus-Distill-GGUF | General | 32GB - 48GB | 122,310 |
| Intel/Qwen3.5-27B-int4-AutoRound | General | 32GB - 48GB | 121,622 |
| unsloth/MiniMax-M2.7-GGUF | text-generation | 8GB (Est.) * | 121,018 |
| black-forest-labs/FLUX.2-klein-9B | image-to-image | 8GB - 16GB | 120,405 |
| zai-org/GLM-4.7 | text-generation | 8GB (Est.) * | 117,371 |
| unsloth/GLM-4.7-Flash-GGUF | text-generation | 8GB (Est.) * | 115,603 |
| RedHatAI/Qwen3.5-122B-A10B-NVFP4 | General | 64GB+ | 115,306 |
| unsloth/Qwen-Image-Edit-2511-GGUF | image-to-image | 8GB (Est.) * | 115,088 |
| rednote-hilab/dots.mocr | image-text-to-text | 8GB (Est.) * | 114,647 |
| TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF | General | 4GB - 8GB | 113,459 |
| zai-org/GLM-5.1 | text-generation | 8GB (Est.) * | 112,939 |
| Qwen/Qwen2.5-Coder-7B-Instruct-GGUF | text-generation | 8GB - 16GB | 111,315 |
| bartowski/google_gemma-4-E2B-it-GGUF | image-text-to-text | 4GB - 8GB | 110,907 |
| llmfan46/gemma-4-26B-A4B-it-uncensored-heretic-GGUF | image-text-to-text | 32GB - 48GB | 106,582 |
| Qwen/Qwen-Image-2512 | text-to-image | 8GB - 12GB | 104,368 |
| litert-community/gemma-4-E2B-it-litert-lm | General | 4GB - 8GB | 103,198 |
| google/gemma-4-26B-A4B | image-text-to-text | 32GB - 48GB | 102,414 |
| RunDiffusion/Juggernaut-XL-v9 | text-to-image | 8GB - 12GB | 100,716 |
| CCSSNE/gemma-4-26B-A4B-it-heretic-ara-gguf | General | 32GB - 48GB | 100,015 |
| Wan-AI/Wan2.2-I2V-A14B-Diffusers | image-to-video | 32GB - 48GB | 99,100 |
| nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 | text-generation | 8GB - 16GB | 96,847 |
| ggml-org/gemma-4-E2B-it-GGUF | General | 4GB - 8GB | 96,412 |
| mlx-community/gemma-4-26b-a4b-it-4bit | image-text-to-text | 32GB - 48GB | 95,733 |
| microsoft/harrier-oss-v1-0.6b | feature-extraction | 8GB - 16GB | 95,315 |
| xinsir/controlnet-union-sdxl-1.0 | text-to-image | 8GB - 12GB | 92,896 |
| prism-ml/Bonsai-8B-gguf | text-generation | 8GB - 16GB | 92,727 |
| Crownelius/Crow-9B-HERETIC-4.6 | General | 8GB - 16GB | 92,059 |
| unsloth/Qwen3.5-397B-A17B-GGUF | image-text-to-text | 64GB+ | 90,480 |
| deepdml/faster-whisper-large-v3-turbo-ct2 | automatic-speech-recognition | 8GB (Est.) * | 89,694 |
| nvidia/llama-nemotron-embed-vl-1b-v2 | sentence-similarity | 4GB - 8GB | 89,253 |
| moonshotai/Kimi-K2-Thinking | text-generation | 8GB (Est.) * | 88,989 |
| llmfan46/gemma-4-31B-it-uncensored-heretic-GGUF | image-text-to-text | 32GB - 48GB | 88,675 |
| dphn/Dolphin-Mistral-24B-Venice-Edition | text-generation | 32GB - 48GB | 86,048 |
| HauhauCS/Qwen3.5-2B-Uncensored-HauhauCS-Aggressive | General | 4GB - 8GB | 85,874 |
| Jackrong/Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-v2-GGUF | image-text-to-text | 8GB - 16GB | 84,954 |
| google/medgemma-1.5-4b-it | image-text-to-text | 8GB - 16GB | 84,831 |
| zeroentropy/zembed-1 | feature-extraction | 2GB - 4GB | 83,783 |
| ibm-granite/granite-4.0-1b-speech | automatic-speech-recognition | 4GB - 8GB | 82,504 |
| nohurry/gemma-4-26B-A4B-it-heretic-GUFF | image-text-to-text | 32GB - 48GB | 81,638 |
| mistralai/Mistral-Small-4-119B-2603 | General | 64GB+ | 80,918 |
| facebook/nllb-200-3.3B | translation | 4GB - 8GB | 78,331 |
| Qwen/Qwen3-Reranker-8B | text-ranking | 8GB - 16GB | 78,327 |
| mlx-community/Qwen3.5-27B-Claude-4.6-Opus-Distilled-MLX-4bit | General | 32GB - 48GB | 78,233 |
| agentscope-ai/QwenPaw-Flash-9B | General | 8GB - 16GB | 77,277 |
| DavidAU/Qwen3.5-9B-Claude-4.6-OS-Auto-Variable-HERETIC-UNCENSORED-THINKING-MAX-NEOCODE-Imatrix-GGUF | image-text-to-text | 8GB - 16GB | 76,951 |
| onnx-community/gemma-4-E2B-it-ONNX | any-to-any | 4GB - 8GB | 75,713 |
| RedHatAI/gemma-4-26B-A4B-it-FP8-Dynamic | General | 32GB - 48GB | 75,498 |
| nvidia/music-flamingo-2601-hf | audio-text-to-text | 4GB - 8GB | 74,884 |
| Qwen/Qwen-Image-Edit | image-to-image | 8GB (Est.) * | 74,190 |
| mlx-community/Qwen3.5-9B-MLX-4bit | image-text-to-text | 8GB - 16GB | 74,174 |
| unsloth/FLUX.2-klein-9B-GGUF | image-to-image | 8GB - 16GB | 74,045 |
| Jiunsong/supergemma4-26b-uncensored-gguf-v2 | text-generation | 32GB - 48GB | 72,519 |
| dphn/Dolphin3.0-Llama3.1-8B | General | 8GB - 16GB | 71,931 |
| facebook/seamless-m4t-v2-large | automatic-speech-recognition | 8GB (Est.) * | 71,242 |
| black-forest-labs/FLUX.2-klein-base-9B | image-to-image | 8GB - 16GB | 70,626 |
| microsoft/bitnet-b1.58-2B-4T-gguf | text-generation | 4GB - 8GB | 70,377 |
| unsloth/NVIDIA-Nemotron-3-Super-120B-A12B-GGUF | text-generation | 64GB+ | 69,949 |
| RedHatAI/gemma-4-31B-it-FP8-block | image-text-to-text | 32GB - 48GB | 69,767 |
| google/gemma-3-1b-pt | text-generation | 4GB - 8GB | 69,743 |
| google/translategemma-4b-it | image-text-to-text | 8GB - 16GB | 69,481 |
| ibm-granite/granite-4.0-3b-vision | image-text-to-text | 4GB - 8GB | 67,011 |
| Arunk25/Qwen-Image-Edit-Rapid-AIO-GGUF | image-text-to-image | 8GB - 12GB | 65,675 |
| unsloth/gemma-4-E4B-it-unsloth-bnb-4bit | image-text-to-text | 8GB - 16GB | 64,263 |
| XiaomiMiMo/MiMo-V2-Flash | text-generation | 8GB (Est.) * | 64,224 |
| TrevorJS/gemma-4-E4B-it-uncensored-GGUF | text-generation | 8GB - 16GB | 63,505 |
| Alissonerdx/BFS-Best-Face-Swap | image-to-image | 8GB (Est.) * | 62,692 |
| ibm-granite/granite-docling-258M | image-text-to-text | 8GB (Est.) * | 60,891 |
| TrevorJS/gemma-4-26B-A4B-it-uncensored-GGUF | text-generation | 32GB - 48GB | 60,711 |
| Serveurperso/ACE-Step-1.5-GGUF | General | 8GB (Est.) * | 60,482 |
| khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled-GGUF | text-generation | 8GB - 16GB | 59,602 |
| fishaudio/s2-pro | text-to-speech | 8GB (Est.) * | 59,349 |
| Tesslate/OmniCoder-9B-GGUF | General | 8GB - 16GB | 58,326 |
| LiquidAI/LFM2.5-VL-450M-GGUF | image-text-to-text | 8GB (Est.) * | 57,911 |
| RedHatAI/Qwen3.6-35B-A3B-NVFP4 | General | 32GB - 48GB | 57,797 |
| unsloth/Llama-3.2-1B-Instruct-GGUF | text-generation | 4GB - 8GB | 57,719 |
| black-forest-labs/FLUX.1-Kontext-dev | image-to-image | 8GB (Est.) * | 57,065 |
| ggml-org/gemma-4-31B-it-GGUF | General | 32GB - 48GB | 56,919 |
| llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic-GGUF | image-text-to-text | 32GB - 48GB | 56,693 |
| DavidAU/Llama-3.2-8X3B-MOE-Dark-Champion-Instruct-uncensored-abliterated-18.4B-GGUF | text-generation | 4GB - 8GB | 56,633 |
| alibaba-pai/Z-Image-Turbo-Fun-Controlnet-Union-2.1 | General | 8GB (Est.) * | 56,471 |
| mradermacher/gemma-4-26B-A4B-it-heretic-GGUF | General | 32GB - 48GB | 56,329 |
| BigDannyPt/Wan-2.2-Remix-GGUF | General | 8GB (Est.) * | 55,999 |
| mlx-community/gemma-4-31b-it-4bit | image-text-to-text | 32GB - 48GB | 55,848 |
| coder3101/gemma-4-26B-A4B-it-heretic | image-text-to-text | 32GB - 48GB | 55,235 |
| stabilityai/stable-diffusion-3.5-large | text-to-image | 8GB - 12GB | 54,115 |
| bartowski/Qwen_Qwen3.6-35B-A3B-GGUF | image-text-to-text | 32GB - 48GB | 52,107 |
| openbmb/VoxCPM2 | text-to-speech | 8GB (Est.) * | 51,554 |
| Jackrong/Qwen3.5-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled | text-generation | 32GB - 48GB | 51,445 |
| Qwen/Qwen3-8B-GGUF | text-generation | 8GB - 16GB | 51,407 |
| unsloth/Qwen3-8B-GGUF | text-generation | 8GB - 16GB | 50,630 |
| microsoft/harrier-oss-v1-270m | feature-extraction | 2GB - 4GB | 50,079 |
| ACE-Step/Ace-Step1.5 | text-to-audio | 4GB - 8GB | 50,056 |
| nvidia/MiniMax-M2.5-NVFP4 | text-generation | 8GB (Est.) * | 49,330 |
| black-forest-labs/FLUX.2-klein-9b-fp8 | image-to-image | 8GB - 16GB | 48,645 |
| prism-ml/Bonsai-8B-mlx-1bit | text-generation | 8GB - 16GB | 48,237 |
| DavidAU/OpenAi-GPT-oss-20b-abliterated-uncensored-NEO-Imatrix-gguf | text-generation | 32GB - 48GB | 48,171 |
| unsloth/Qwen-Image-2512-GGUF | text-to-image | 8GB - 12GB | 47,956 |
| unsloth/Z-Image-Turbo-GGUF | text-to-image | 8GB - 12GB | 47,609 |
| LiquidAI/LFM2.5-1.2B-Thinking-GGUF | text-generation | 4GB - 8GB | 47,321 |
| TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill-GGUF | text-generation | 32GB - 48GB | 47,028 |
| LiquidAI/LFM2.5-350M | text-generation | 8GB (Est.) * | 46,926 |
| koboldcpp/tts | General | 8GB (Est.) * | 45,834 |
| DavidAU/GLM-4.7-Flash-Uncensored-Heretic-NEO-CODE-Imatrix-MAX-GGUF | text-generation | 8GB (Est.) * | 45,069 |
| Kijai/LTXV2_comfy | General | 8GB (Est.) * | 43,668 |
| Tongyi-MAI/Z-Image | text-to-image | 8GB - 12GB | 43,665 |
| tarn59/pixel_art_style_lora_z_image_turbo | text-to-image | 8GB - 12GB | 43,181 |
| unsloth/FLUX.2-klein-4B-GGUF | image-to-image | 8GB - 16GB | 43,059 |
| unsloth/GLM-5.1-GGUF | text-generation | 8GB (Est.) * | 42,667 |
| OpenMOSS-Team/MOSS-TTS | text-to-speech | 8GB (Est.) * | 42,361 |
| dphn/Dolphin3.0-Llama3.1-8B-GGUF | General | 8GB - 16GB | 41,877 |
| litert-community/gemma-4-E4B-it-litert-lm | General | 8GB - 16GB | 41,869 |
| RedHatAI/gemma-4-31B-it-NVFP4 | image-text-to-text | 32GB - 48GB | 41,671 |
| facebook/sam3.1 | mask-generation | 8GB (Est.) * | 41,304 |
| mlx-community/gemma-4-e4b-it-4bit | any-to-any | 8GB - 16GB | 41,040 |
| black-forest-labs/FLUX.2-small-decoder | image-to-image | 8GB (Est.) * | 40,538 |
| protonx-models/protonx-legal-tc | General | 8GB (Est.) * | 40,213 |
| unsloth/Devstral-Small-2-24B-Instruct-2512-GGUF | General | 32GB - 48GB | 38,827 |
| Jackrong/Gemopus-4-26B-A4B-it-GGUF | text-generation | 32GB - 48GB | 38,629 |
| cyankiwi/MiniMax-M2.7-AWQ-4bit | text-generation | 8GB - 16GB | 37,637 |
| TeichAI/gemma-4-26B-A4B-it-Claude-Opus-Distill-GGUF | General | 32GB - 48GB | 37,606 |
| OBLITERATUS/gemma-4-E4B-it-OBLITERATED | text-generation | 8GB - 16GB | 37,130 |
| MiniMaxAI/MiniMax-M2.1 | text-generation | 8GB (Est.) * | 36,798 |
| stabilityai/stable-video-diffusion-img2vid | image-to-video | 8GB (Est.) * | 36,513 |
| Qwen/Qwen3-Embedding-0.6B-GGUF | General | 8GB - 16GB | 36,502 |
| nvidia/Cosmos-Predict2.5-2B | General | 4GB - 8GB | 36,263 |
| OpenMOSS-Team/MOSS-TTS-Nano-100M | text-to-speech | 8GB (Est.) * | 36,158 |
| dealignai/Gemma-4-26B-A4B-JANG_4M-CRACK | image-text-to-text | 32GB - 48GB | 35,176 |
| zai-org/CogVideoX-5b | text-to-video | 8GB - 16GB | 35,051 |
| llm-jp/llm-jp-4-8b-thinking | text-generation | 8GB - 16GB | 34,854 |
| google/medgemma-27b-text-it | text-generation | 32GB - 48GB | 34,835 |
| google/functiongemma-270m-it | text-generation | 8GB (Est.) * | 34,551 |
| QuantStack/LTX-2.3-GGUF | image-to-video | 8GB (Est.) * | 34,461 |
| fal/Qwen-Image-Edit-2511-Multiple-Angles-LoRA | image-to-image | 8GB (Est.) * | 34,408 |
| microsoft/harrier-oss-v1-27b | feature-extraction | 32GB - 48GB | 32,949 |
| huihui-ai/Huihui-gpt-oss-20b-BF16-abliterated | text-generation | 32GB - 48GB | 32,756 |
| OpenMOSS-Team/MOSS-Audio-Tokenizer-Nano | feature-extraction | 2GB - 4GB | 32,462 |
| mradermacher/gemma-4-19b-a4b-it-REAP-i1-GGUF | General | 32GB - 48GB | 31,640 |
| Jackrong/Qwopus3.5-4B-v3-GGUF | image-text-to-text | 8GB - 16GB | 31,358 |
| Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2 | image-text-to-text | 8GB - 16GB | 30,935 |
| Jackrong/Qwopus3.5-27B-v3 | image-text-to-text | 32GB - 48GB | 30,464 |
| prithivMLmods/Qwen-Image-Edit-2511-Ultra-Realistic-Portrait | image-to-image | 8GB (Est.) * | 30,108 |
| unsloth/Ministral-3-3B-Instruct-2512-GGUF | General | 4GB - 8GB | 29,603 |
| lerobot/smolvla_base | robotics | 8GB (Est.) * | 29,504 |
| mistralai/Voxtral-Small-24B-2507 | audio-text-to-text | 32GB - 48GB | 29,431 |
| mradermacher/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-GGUF | General | 8GB - 16GB | 29,398 |
| huggingface/CodeBERTa-small-v1 | fill-mask | 8GB (Est.) * | 29,368 |
| lukealonso/GLM-5.1-NVFP4 | General | 8GB (Est.) * | 29,326 |
| Qwen/Qwen3-Omni-30B-A3B-Thinking | any-to-any | 32GB - 48GB | 29,014 |
| bartowski/Qwen2.5-14B-Instruct-GGUF | text-generation | 32GB - 48GB | 28,899 |
| huihui-ai/Huihui-Qwen3.5-35B-A3B-abliterated | image-text-to-text | 32GB - 48GB | 28,778 |
| mudler/Qwen3.6-35B-A3B-APEX-GGUF | General | 32GB - 48GB | 28,771 |
| cyankiwi/gemma-4-31B-it-AWQ-8bit | image-text-to-text | 32GB - 48GB | 28,598 |
| bartowski/DeepSeek-R1-Distill-Qwen-32B-abliterated-GGUF | text-generation | 32GB - 48GB | 28,312 |
| lukealonso/MiniMax-M2.7-NVFP4 | General | 8GB (Est.) * | 28,281 |
| Jackrong/Gemopus-4-E4B-it-GGUF | image-text-to-text | 8GB - 16GB | 28,111 |
| TrevorJS/gemma-4-31B-it-uncensored-GGUF | text-generation | 32GB - 48GB | 26,820 |
| unsloth/ERNIE-Image-Turbo-GGUF | text-to-image | 8GB - 12GB | 26,394 |
| valiantcat/LTX-2.3-Transition-LORA | image-to-video | 8GB (Est.) * | 25,921 |
| mlx-community/Qwen3.6-35B-A3B-4bit | image-text-to-text | 32GB - 48GB | 25,649 |
| opendatalab/MinerU2.5-Pro-2604-1.2B | image-text-to-text | 4GB - 8GB | 25,575 |
| openbmb/MiniCPM-o-4_5 | any-to-any | 8GB (Est.) * | 25,100 |
| mlx-community/Qwen3.6-35B-A3B-nvfp4 | image-text-to-text | 32GB - 48GB | 24,211 |
| dealignai/Gemma-4-26B-A4B-JANG_2L-CRACK | image-text-to-text | 32GB - 48GB | 24,117 |
| xai-org/grok-2 | General | 8GB (Est.) * | 23,426 |
| Wan-AI/Wan2.2-Animate-14B | video-to-video | 32GB - 48GB | 23,266 |
| RedHatAI/gemma-4-31B-it-speculator.eagle3 | General | 32GB - 48GB | 22,740 |
| bigatuna/Qwen3.5-9b-Sushi-Coder-RL-GGUF | text-generation | 8GB - 16GB | 22,132 |
| Qwen/Qwen-Image-Layered | image-text-to-image | 8GB - 12GB | 22,039 |
| TeichAI/gemma-4-26B-A4B-it-Claude-Opus-Distill-v2-GGUF | General | 32GB - 48GB | 21,978 |
| CohereLabs/c4ai-command-r7b-12-2024 | text-generation | 8GB - 16GB | 21,326 |
| Tesslate/OmniCoder-9B | text-generation | 8GB - 16GB | 21,281 |
| tvall43/Qwen3.5-14B-A3B-Claude-4.6-Opus-Reasoning-Distilled-reap-gguf | text-generation | 32GB - 48GB | 21,055 |
| mudler/gemma-4-26B-A4B-it-heretic-APEX-GGUF | General | 32GB - 48GB | 20,710 |
| Jackrong/MLX-Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit | text-generation | 32GB - 48GB | 20,426 |
| Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1-GGUF | image-text-to-text | 8GB - 16GB | 20,291 |
| arcee-ai/Trinity-Large-Thinking | text-generation | 8GB (Est.) * | 20,087 |
| LiquidAI/LFM2.5-VL-450M | image-text-to-text | 8GB (Est.) * | 20,008 |
| unsloth/GLM-4.7-Flash-REAP-23B-A3B-GGUF | text-generation | 32GB - 48GB | 19,959 |
| deepseek-ai/DeepSeek-V3.2-Speciale | text-generation | 8GB (Est.) * | 19,235 |
| bartowski/Qwen2.5.1-Coder-7B-Instruct-GGUF | text-generation | 8GB - 16GB | 19,212 |
| sarvamai/sarvam-105b | text-generation | 64GB+ | 19,096 |
| Intel/gemma-4-31B-it-int4-AutoRound | General | 32GB - 48GB | 18,988 |
| huihui-ai/Huihui-Qwen3.5-27B-Claude-4.6-Opus-abliterated | image-text-to-text | 32GB - 48GB | 18,964 |
| LiquidAI/LFM2.5-350M-GGUF | text-generation | 8GB (Est.) * | 18,719 |
| Prior-Labs/TabPFN-v2-clf | tabular-classification | 8GB (Est.) * | 18,638 |
| ai-sage/GigaChat3.1-10B-A1.8B-GGUF | text-generation | 32GB - 48GB | 18,605 |
| Lightricks/LTX-2.3-nvfp4 | image-to-video | 8GB (Est.) * | 18,508 |
| prism-ml/Bonsai-1.7B-gguf | text-generation | 8GB - 16GB | 17,892 |
| LyliaEngine/Pony_Diffusion_V6_XL | text-to-image | 8GB - 12GB | 17,775 |
| IndexTeam/IndexTTS-2 | text-to-speech | 8GB (Est.) * | 17,577 |
| cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit | image-text-to-text | 32GB - 48GB | 17,492 |
| Lewdiculous/L3-8B-Stheno-v3.2-GGUF-IQ-Imatrix | General | 8GB - 16GB | 17,097 |
| BugTraceAI/BugTraceAI-Apex-G4-26B-Q4 | General | 32GB - 48GB | 17,035 |
| Aero-Ex/Trellis2-GGUF | General | 8GB (Est.) * | 16,950 |
| meituan-longcat/LongCat-Next | any-to-any | 8GB (Est.) * | 16,781 |
| z-lab/Qwen3.5-27B-DFlash | text-generation | 32GB - 48GB | 16,656 |
| RedHatAI/Qwen3-Coder-Next-NVFP4 | text-generation | 8GB (Est.) * | 16,621 |
| google/translategemma-12b-it | image-text-to-text | 32GB - 48GB | 16,383 |
| TheCluster/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-MLX-mxfp8 | image-text-to-text | 8GB - 16GB | 16,273 |
| dx8152/Flux2-Klein-9B-Consistency | image-to-image | 8GB - 16GB | 16,255 |
| coder3101/gemma-4-31B-it-heretic | image-text-to-text | 32GB - 48GB | 16,237 |
| jinaai/ReaderLM-v2 | text-generation | 8GB (Est.) * | 16,233 |
| Jiunsong/supergemma4-26b-uncensored-mlx-4bit-v2 | text-generation | 32GB - 48GB | 16,017 |
| lightx2v/Wan2.2-Distill-Models | General | 8GB (Est.) * | 16,007 |
| kernels-community/flash-attn2 | General | 8GB (Est.) * | 15,892 |
| QuantTrio/Qwen3.6-35B-A3B-AWQ | image-text-to-text | 32GB - 48GB | 15,572 |
| mradermacher/Gemma-4-Queen-31B-it-i1-GGUF | any-to-any | 32GB - 48GB | 15,538 |
| black-forest-labs/FLUX.2-klein-9b-kv | image-to-image | 8GB - 16GB | 15,338 |
| wikeeyang/Flux2-Klein-9B-True-V2 | text-to-image | 8GB - 16GB | 15,195 |
| nvidia/nemotron-speech-streaming-en-0.6b | automatic-speech-recognition | 8GB - 16GB | 14,913 |
| kyutai/pocket-tts | General | 8GB (Est.) * | 14,893 |
| OpenMOSS-Team/MOSS-TTS-Realtime | text-to-speech | 8GB (Est.) * | 14,566 |
| DeepHat/DeepHat-V1-7B | text-generation | 8GB - 16GB | 14,534 |
| saricles/Qwen3-Coder-Next-NVFP4-GB10 | text-generation | 8GB (Est.) * | 14,274 |
| tencent/HY-MT1.5-1.8B-GGUF | translation | 8GB - 16GB | 14,094 |
| Jackrong/Qwopus3.5-27B-v3-FP8-vllm-ready | text-generation | 32GB - 48GB | 13,796 |
| Rta-AILabs/Nandi-Mini-150M | text-generation | 8GB (Est.) * | 13,677 |
| z-lab/gemma-4-31B-it-PARO | image-text-to-text | 32GB - 48GB | 13,539 |
| ManniX-ITA/gemma-4-A4B-98e-v3-it-GGUF | General | 8GB - 16GB | 13,517 |
| onnx-community/Bonsai-1.7B-ONNX | text-generation | 8GB - 16GB | 13,491 |
| RedHatAI/gemma-4-31B-it-FP8-Dynamic | General | 32GB - 48GB | 13,217 |
| nvidia/gliner-PII | token-classification | 8GB (Est.) * | 12,932 |
| tiiuae/Falcon-Perception | mask-generation | 8GB (Est.) * | 12,918 |
| DavidAU/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking | image-text-to-text | 64GB+ | 12,820 |
| prithivMLmods/chandra-ocr-2-GGUF | image-text-to-text | 8GB (Est.) * | 12,792 |
| prism-ml/Bonsai-4B-gguf | text-generation | 8GB - 16GB | 12,582 |
| mradermacher/gemma-4-19B-A4B-it-The-DECKARD-Heretic-Uncensored-Thinking-i1-GGUF | General | 32GB - 48GB | 12,422 |
| mradermacher/gemma-4-26B-A4B-it-heretic-ara-v2-i1-GGUF | General | 32GB - 48GB | 12,399 |
| FireRedTeam/FireRed-Image-Edit-1.1 | image-to-image | 8GB (Est.) * | 12,386 |
| bartowski/MiniMaxAI_MiniMax-M2.7-GGUF | text-generation | 8GB (Est.) * | 12,314 |
| lerobot/pi05_base | robotics | 8GB (Est.) * | 12,110 |
| jayn7/WAN2.2-I2V_A14B-DISTILL-LIGHTX2V-4STEP-GGUF | image-to-video | 32GB - 48GB | 11,877 |
| TheDrummer/Skyfall-31B-v4.2-GGUF | General | 32GB - 48GB | 11,865 |
| tiiuae/Falcon-OCR | image-to-text | 8GB (Est.) * | 11,777 |
| lilylilith/AnyPose | image-to-image | 8GB (Est.) * | 11,733 |
| alibaba-pai/Z-Image-Fun-Lora-Distill | text-to-image | 8GB - 12GB | 11,715 |
| Hcompany/Holo3-35B-A3B | image-text-to-text | 32GB - 48GB | 11,665 |
| AxionML/Qwen3.5-27B-NVFP4 | image-text-to-text | 32GB - 48GB | 11,557 |
| mradermacher/gemma-4-26B-A4B-it-ultra-uncensored-heretic-i1-GGUF | General | 32GB - 48GB | 11,295 |
| bartowski/TheDrummer_Rocinante-X-12B-v1-GGUF | text-generation | 32GB - 48GB | 10,912 |
| mradermacher/Qwopus3.5-27B-v3-i1-GGUF | General | 32GB - 48GB | 10,836 |
| ByteDance-Seed/BAGEL-7B-MoT | any-to-any | 8GB - 16GB | 10,743 |
| Abiray/gemma-4-E4B-it-OBLITERATED-GGUF | text-generation | 8GB - 16GB | 10,486 |
| LuffyTheFox/Qwen3.6-35B-A3B-Uncensored-Wasserstein-GGUF | image-text-to-text | 32GB - 48GB | 10,214 |
| byteshape/Qwen3.5-35B-A3B-GGUF | image-text-to-text | 32GB - 48GB | 10,212 |
| ibm-granite/granitelib-rag-r1.0 | General | 8GB (Est.) * | 10,205 |
| YTan2000/Qwen3.5-27B-TQ3_1S | image-text-to-text | 32GB - 48GB | 10,051 |
| LiquidAI/LFM2.5-Audio-1.5B-GGUF | General | 8GB - 16GB | 9,993 |
| kai-os/Carnice-9b-GGUF | text-generation | 8GB - 16GB | 9,964 |
| FireRedTeam/FireRed-Image-Edit-1.1-ComfyUI | General | 8GB (Est.) * | 9,850 |
| DavidAU/gemma-4-31B-it-The-DECKARD-HERETIC-UNCENSORED-Thinking | image-text-to-text | 32GB - 48GB | 9,765 |
| deadbydawn101/gemma-4-E4B-Agentic-Opus-Reasoning-GeminiCLI-mlx-4bit | text-generation | 8GB - 16GB | 9,692 |
| TeichAI/gemma-4-31B-it-Claude-Opus-Distill-v2-GGUF | General | 32GB - 48GB | 9,671 |
| samuelcardillo/Qwen3-Coder-Next-Opus-4.6-Reasoning-Distilled-GGUF | General | 8GB (Est.) * | 9,484 |
| Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-GGUF | text-generation | 32GB - 48GB | 9,453 |
| nvidia/NVIDIA-Nemotron-Parse-v1.2 | image-text-to-text | 8GB (Est.) * | 9,379 |
| HauhauCS/GPTOSS-120B-Uncensored-HauhauCS-Aggressive | General | 64GB+ | 9,353 |
| HauhauCS/Qwen3VL-8B-Uncensored-HauhauCS-Aggressive | General | 8GB - 16GB | 9,320 |
| ruv/ruvltra-claude-code | text-generation | 8GB (Est.) * | 9,215 |
| DavidAU/gemma-4-31B-it-Mystery-Fine-Tune-HERETIC-UNCENSORED-Thinking | image-text-to-text | 32GB - 48GB | 9,199 |
| AesSedai/Qwen3.5-35B-A3B-GGUF | General | 32GB - 48GB | 9,119 |
| danielcherubini/Qwen3.5-DeltaCoder-9B-GGUF | text-generation | 8GB - 16GB | 9,119 |
| LGAI-EXAONE/EXAONE-4.5-33B | image-text-to-text | 32GB - 48GB | 8,975 |
| Jiunsong/supergemma4-26b-abliterated-multimodal-gguf-4bit | image-text-to-text | 32GB - 48GB | 8,917 |
| meituan-longcat/LongCat-AudioDiT-1B | General | 4GB - 8GB | 8,804 |
| DJLougen/Harmonic-Hermes-9B-GGUF | General | 8GB - 16GB | 8,708 |
| rodrigomt/s2-pro-gguf | text-to-speech | 8GB (Est.) * | 8,636 |
| NousResearch/Hermes-4.3-36B | text-generation | 64GB+ | 8,572 |
| Wan-AI/Wan2.2-I2V-A14B | image-to-video | 32GB - 48GB | 8,380 |
| elix3r/LTX-2.3-22b-AV-LoRA-talking-head | image-to-video | 32GB - 48GB | 8,099 |
| arcee-ai/Trinity-Large-Thinking-GGUF | General | 8GB (Est.) * | 8,055 |
| z-lab/Qwen3.5-4B-DFlash | text-generation | 8GB - 16GB | 8,050 |
| mistralai/Voxtral-4B-TTS-2603 | text-to-speech | 8GB - 16GB | 8,030 |
| LGAI-EXAONE/EXAONE-4.5-33B-GGUF | image-text-to-text | 32GB - 48GB | 7,893 |
| unsloth/ERNIE-Image-GGUF | text-to-image | 8GB - 12GB | 7,808 |
| Jiunsong/SuperGemma4-31b-abliterated-GGUF | text-generation | 32GB - 48GB | 7,683 |
| unsloth/medgemma-1.5-4b-it-GGUF | image-text-to-text | 8GB - 16GB | 7,671 |
| moondream/moondream3-preview | image-text-to-text | 8GB (Est.) * | 7,645 |
| mradermacher/gemma-4-21b-a4b-it-REAP-heretic-i1-GGUF | General | 32GB - 48GB | 7,614 |
| ACE-Step/acestep-5Hz-lm-4B | text-to-audio | 8GB - 16GB | 7,442 |
| z-lab/Qwen3.5-9B-DFlash | text-generation | 8GB - 16GB | 7,163 |
| Jiunsong/supergemma4-26b-abliterated-multimodal | text-generation | 32GB - 48GB | 7,154 |
| MediaTek-Research/Breeze-ASR-25 | automatic-speech-recognition | 8GB (Est.) * | 6,982 |
| unsloth/Devstral-2-123B-Instruct-2512-GGUF | General | 64GB+ | 6,844 |
| PaddlePaddle/PaddleOCR-VL | image-text-to-text | 8GB (Est.) * | 6,842 |
| Wan-AI/Wan2.2-TI2V-5B | text-to-video | 8GB - 16GB | 6,789 |
| GuangyuanSD/Z-Image-Distilled | text-to-image | 8GB - 12GB | 6,787 |
| nvidia/NV-Generate-CT | General | 8GB (Est.) * | 6,643 |
| ACE-Step/acestep-transcriber | audio-text-to-text | 4GB - 8GB | 6,535 |
| DJLougen/Ornstein-27B-v2-GGUF | image-text-to-text | 32GB - 48GB | 6,489 |
| LiquidAI/LFM2-2.6B | text-generation | 8GB - 16GB | 6,435 |
| LiconStudio/Ltx2.3-VBVR-lora-I2V | General | 8GB (Est.) * | 6,396 |
| kai-os/Carnice-9b | text-generation | 8GB - 16GB | 6,327 |
| fal/FLUX.2-dev-Turbo | text-to-image | 8GB - 12GB | 6,322 |
| Wan-AI/Wan2.2-T2V-A14B | text-to-video | 32GB - 48GB | 6,300 |
| Jackrong/Qwopus3.5-27B-v3.5-GGUF | image-text-to-text | 32GB - 48GB | 6,270 |
| inferencerlabs/GLM-5.1-MLX-4.8bit-INF | text-generation | 8GB - 16GB | 6,258 |
| ykarout/Qwen3.5-9b-Opus-Openclaw-Distilled-GGUF | text-generation | 8GB - 16GB | 6,179 |
| mradermacher/Huihui-gemma-4-E4B-it-abliterated-GGUF | General | 8GB - 16GB | 6,157 |
| Jackrong/MLX-Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled-v2-4bit | text-generation | 8GB - 16GB | 6,132 |
| istupakov/parakeet-tdt-0.6b-v3-onnx | automatic-speech-recognition | 8GB - 16GB | 6,120 |
| zerofata/G4-MeroMero-26B-A4B-gguf | General | 32GB - 48GB | 6,105 |
| deadbydawn101/gemma-4-E2B-Heretic-Uncensored-mlx-4bit | image-text-to-text | 4GB - 8GB | 6,026 |
| MaxedOut/ComfyUI-Starter-Packs | text-to-image | 8GB - 12GB | 5,999 |
| ByteDance/Ouro-2.6B-Thinking | text-generation | 8GB - 16GB | 5,991 |
| google/gemma-3n-E2B-it-litert-lm | text-generation | 4GB - 8GB | 5,979 |
| AesSedai/Qwen3.6-35B-A3B-GGUF | General | 32GB - 48GB | 5,881 |
| jdopensource/JoyAI-Image-Edit | image-to-image | 8GB (Est.) * | 5,835 |
| drbaph/OmniVoice-bf16 | text-to-speech | 8GB (Est.) * | 5,789 |
| kai-os/Carnice-27b-GGUF | text-generation | 32GB - 48GB | 5,740 |
| nvidia/music-flamingo-hf | audio-text-to-text | 4GB - 8GB | 5,696 |
| 0xSero/Qwen3.5-122B-A10B-REAP-20-GGUF | General | 64GB+ | 5,678 |
| ACE-Step/acestep-v15-xl-turbo | text-to-audio | 4GB - 8GB | 5,622 |
| tencent/HunyuanImage-3.0-Instruct | image-to-image | 8GB (Est.) * | 5,563 |
| google/tipsv2-b14 | zero-shot-image-classification | 8GB (Est.) * | 5,526 |
| mmangkad/Qwen3.6-35B-A3B-NVFP4 | text-generation | 32GB - 48GB | 5,516 |
| Abiray/Qwen3.6-35B-A3B-heretic-GGUF | image-text-to-text | 32GB - 48GB | 5,443 |
| meituan-longcat/LongCat-AudioDiT-3.5B | General | 8GB - 16GB | 5,437 |
| llmfan46/Gemma-4-Garnet-31B-it-uncensored-heretic-GGUF | text-generation | 32GB - 48GB | 5,379 |
| mradermacher/gemma-4-26B-A4B-it-ultra-uncensored-heretic-GGUF | General | 32GB - 48GB | 5,358 |
| bigatuna/Qwen3.5-27b-Sushi-Coder-RL-GGUF | text-generation | 32GB - 48GB | 5,342 |
| genmo/mochi-1-preview | text-to-video | 8GB (Est.) * | 5,317 |
| AesSedai/MiniMax-M2.7-GGUF | General | 8GB (Est.) * | 5,266 |
| Youssofal/Qwen3.6-35B-A3B-Abliterated-Heretic-MLX-4bit | text-generation | 32GB - 48GB | 5,181 |
| TrevorJS/gemma-4-31B-it-uncensored | text-generation | 32GB - 48GB | 5,174 |
| mlx-community/Voxtral-4B-TTS-2603-mlx-4bit | text-to-speech | 8GB - 16GB | 5,145 |
| allenai/Olmo-3.1-32B-Think | text-generation | 32GB - 48GB | 5,122 |
| 0xSero/gemma-4-21b-a4b-it-REAP | text-generation | 32GB - 48GB | 5,064 |
| Ex0bit/Gemma4-26B-A4B-PRISM-PRO-DQ-GGUF | image-text-to-text | 4GB - 8GB | 5,021 |
| z-lab/Qwen3.5-35B-A3B-DFlash | text-generation | 32GB - 48GB | 4,994 |
| samuelcardillo/Carnice-MoE-35B-A3B-GGUF | General | 32GB - 48GB | 4,993 |
| mlx-community/MiniMax-M2.7-4bit-mxfp4 | text-generation | 8GB - 16GB | 4,972 |
| Jackrong/Qwopus3.5-27B-v3-FP8 | image-text-to-text | 32GB - 48GB | 4,938 |
| prism-ml/Ternary-Bonsai-8B-mlx-2bit | text-generation | 8GB - 16GB | 4,930 |
| unsloth/Qwen3.6-35B-A3B-MLX-8bit | image-text-to-text | 32GB - 48GB | 4,920 |
| unsloth/Qwen3.6-35B-A3B-UD-MLX-4bit | image-text-to-text | 32GB - 48GB | 4,893 |
| Jundot/Qwen3.6-35B-A3B-oQ6 | General | 32GB - 48GB | 4,880 |
| Intelligent-Internet/II-Medical-8B | text-generation | 8GB - 16GB | 4,845 |
| TrevorJS/gemma-4-E4B-it-uncensored | text-generation | 8GB - 16GB | 4,784 |
| chromadb/context-1 | text-generation | 8GB (Est.) * | 4,782 |
| froggeric/Qwen3.5-35B-A3B-Uncensored-FernflowerAI-MLX-8bit | image-text-to-text | 32GB - 48GB | 4,773 |
| baidu/ERNIE-Image-Turbo | text-to-image | 8GB - 12GB | 4,757 |
| Youssofal/MiniMax-M2.7-Abliterated-Heretic-GGUF | text-generation | 8GB (Est.) * | 4,721 |
| LiquidAI/LFM2-8B-A1B-GGUF | text-generation | 8GB - 16GB | 4,709 |
| palmfuture/Qwen3.6-35B-A3B-GPTQ-Int4 | image-text-to-text | 32GB - 48GB | 4,705 |
| bigatuna/Qwen3.5-9b-Sushi-Coder-RL-MLX | text-generation | 8GB - 16GB | 4,604 |
| mudler/Carnice-MoE-35B-A3B-APEX-GGUF | General | 32GB - 48GB | 4,558 |
| onnx-community/chatterbox-multilingual-ONNX | text-to-speech | 8GB (Est.) * | 4,557 |
| unsloth/Qwen3.6-35B-A3B | image-text-to-text | 32GB - 48GB | 4,511 |
| anrilombard/mzansilm-125m | text-generation | 8GB (Est.) * | 4,411 |
| p-e-w/gemma-4-E2B-it-heretic-ara | any-to-any | 4GB - 8GB | 4,269 |
| wangzhang/gemma-4-31B-it-abliterated | General | 32GB - 48GB | 4,259 |
| JANGQ-AI/MiniMax-M2.7-JANGTQ | text-generation | 8GB (Est.) * | 4,255 |
| caiovicentino1/Qwen3.6-35B-A3B-HLWQ-CT-INT4 | text-generation | 32GB - 48GB | 4,223 |
| huihui-ai/Huihui-gemma-4-31B-it-abliterated | any-to-any | 32GB - 48GB | 4,211 |
| mlx-community/Qwen3.6-35B-A3B-4bit-DWQ | text-generation | 32GB - 48GB | 4,184 |
| stabilityai/stable-diffusion-3-medium | text-to-image | 8GB - 12GB | 4,160 |
| ubergarm/MiniMax-M2.7-GGUF | text-generation | 8GB (Est.) * | 3,997 |
| huihui-ai/Huihui-Qwopus3.5-9B-v3-abliterated | image-text-to-text | 8GB - 16GB | 3,993 |
| Jiunsong/supergemma4-26b-abliterated-multimodal-mlx-4bit | image-text-to-text | 32GB - 48GB | 3,947 |
| unsloth/MiMo-V2-Flash-GGUF | General | 8GB (Est.) * | 3,928 |
| TheDrummer/Cydonia-24B-v4.3 | General | 32GB - 48GB | 3,922 |
| Jiunsong/supergemma4-26b-abliterated-multimodal-gguf-8bit | image-text-to-text | 32GB - 48GB | 3,858 |
| ACE-Step/acestep-v15-xl-sft | text-to-audio | 4GB - 8GB | 3,776 |
| JANGQ-AI/MiniMax-M2.7-JANG_2L | text-generation | 8GB (Est.) * | 3,771 |
| baidu/ERNIE-Image | text-to-image | 8GB - 12GB | 3,761 |
| Jackrong/Qwen3.5-9B-GLM5.1-Distill-v1 | image-text-to-text | 8GB - 16GB | 3,730 |
| nvidia/GR00T-N1.7-3B | robotics | 4GB - 8GB | 3,723 |
| zai-org/GLM-Image | text-to-image | 8GB - 12GB | 3,668 |
| Jackrong/Gemopus-4-31B-it-GGUF | text-generation | 32GB - 48GB | 3,642 |
| coder3101/Qwen3.5-27B-heretic | image-text-to-text | 32GB - 48GB | 3,548 |
| google/tipsv2-l14 | zero-shot-image-classification | 8GB (Est.) * | 3,524 |
| allenai/MolmoWeb-8B | image-text-to-text | 8GB - 16GB | 3,448 |
| YTan2000/Qwen3.6-35B-A3B-TQ3_4S | image-text-to-text | 32GB - 48GB | 3,410 |
| invincibleambuj/Ambuj-Tripathi-Indian-Legal-Llama-GGUF | General | 8GB (Est.) * | 3,393 |
| sakamakismile/Qwen3.6-35B-A3B-NVFP4 | image-text-to-text | 32GB - 48GB | 3,358 |
| ggml-org/Qwen3-ASR-1.7B-GGUF | General | 8GB - 16GB | 3,326 |
| Rta-AILabs/Nandi-Mini-150M-Instruct | text-generation | 8GB (Est.) * | 3,314 |
| Abiray/Qwen3.6-35B-A3B-Q4_K_M-GGUF | image-text-to-text | 32GB - 48GB | 3,206 |
| bluryar/VoxCPM-GGUF | text-to-speech | 8GB (Est.) * | 3,177 |
| RedHatAI/Qwen3.5-35B-A3B-FP8-dynamic | image-text-to-text | 32GB - 48GB | 3,126 |
| mudler/MiniMax-M2.7-APEX-GGUF | General | 8GB (Est.) * | 3,096 |
| prism-ml/Bonsai-4B-mlx-1bit | text-generation | 8GB - 16GB | 3,005 |
| Jackrong/Qwopus-GLM-18B-Merged-GGUF | text-generation | 32GB - 48GB | 2,975 |
| JANGQ-AI/MiniMax-M2.7-JANG_3L | text-generation | 8GB (Est.) * | 2,957 |
| ACE-Step/acestep-captioner | text-to-audio | 4GB - 8GB | 2,948 |
| llmfan46/Gemma-4-Queen-31B-it-uncensored-heretic-GGUF | image-text-to-text | 32GB - 48GB | 2,883 |
| unsloth/gemma-4-E4B-it-UD-MLX-4bit | image-text-to-text | 8GB - 16GB | 2,860 |
| NousResearch/Hermes-4-14B | text-generation | 32GB - 48GB | 2,817 |
| Jiunsong/SuperGemma4-31b-abliterated-mlx-4bit | text-generation | 32GB - 48GB | 2,813 |
| Jundot/Qwen3.6-35B-A3B-oQ4 | General | 32GB - 48GB | 2,754 |
| noctrex/Qwen3.6-35B-A3B-MXFP4_MOE-GGUF | image-text-to-text | 32GB - 48GB | 2,721 |
| DJLougen/Ornstein3.6-35B-A3B-GGUF | text-generation | 32GB - 48GB | 2,692 |
| ggml-org/Qwen3-Omni-30B-A3B-Instruct-GGUF | General | 32GB - 48GB | 2,686 |
| RomixERR/Pornmaster_v1-Z-Images-Turbo | text-to-image | 8GB - 12GB | 2,661 |
| prithivMLmods/gemma-4-31B-it-NVFP4 | image-text-to-text | 32GB - 48GB | 2,649 |
| caiovicentino1/Huihui-Qwopus3.5-27B-v3-abliterated-HLWQ-Q5 | text-generation | 32GB - 48GB | 2,641 |
| CISCai/gemma-4-31B-it-NVFP4-turbo-GGUF | text-generation | 32GB - 48GB | 2,564 |
| Arunk25/Qwen_Image_Edit-Remix-v2_0_GGUF | image-text-to-image | 8GB - 12GB | 2,559 |
| Overworld/Waypoint-1.5-1B | General | 4GB - 8GB | 2,555 |
| ByteDance-Seed/SeedVR2-3B | video-to-video | 4GB - 8GB | 2,514 |
| zed-industries/zeta-2 | text-generation | 8GB (Est.) * | 2,466 |
| carsenk/llama3.2_1b_2025_uncensored_v2 | text-generation | 4GB - 8GB | 2,461 |
| squ11z1/claude-oss | text-generation | 8GB (Est.) * | 2,424 |
| yifanyu/I-DLM-8B | text-generation | 8GB - 16GB | 2,398 |
| Jackrong/Qwen3.5-27B-GLM5.1-Distill-v1-GGUF | image-text-to-text | 32GB - 48GB | 2,315 |
| wikeeyang/Magic-Wan-T2IV-V3 | text-to-image | 8GB - 12GB | 2,272 |
| llm-jp/llm-jp-4-8b-instruct | text-generation | 8GB - 16GB | 2,254 |
| TeichAI/gemma-4-26B-A4B-it-Claude-Opus-Distill | image-text-to-text | 32GB - 48GB | 2,226 |
| fno2010/MiniMax-M2.7-TQ3 | General | 8GB (Est.) * | 2,163 |
| z-lab/Qwen3.6-35B-A3B-DFlash | text-generation | 32GB - 48GB | 2,156 |
| huihui-ai/Huihui-gemma-4-E4B-it-abliterated | any-to-any | 8GB - 16GB | 2,129 |
| FINAL-Bench/Darwin-31B-Opus | text-generation | 32GB - 48GB | 2,082 |
| AIDC-AI/Marco-Nano-Instruct | text-generation | 8GB (Est.) * | 2,045 |
| Abiray/LTX-2.3-22B-DISTILLED-1.1-GGUF | text-to-video | 32GB - 48GB | 2,042 |
| Jiunsong/supergemma4-26b-abliterated-multimodal-mlx-8bit | image-text-to-text | 32GB - 48GB | 2,011 |
| ACE-Step/acestep-v15-xl-base | text-to-audio | 4GB - 8GB | 1,980 |
| Bedovyy/ERNIE-Image-Quantized | text-to-image | 8GB - 12GB | 1,951 |
| Bedovyy/Anima-FP8 | text-to-image | 8GB - 12GB | 1,933 |
| Abiray/Qwen3.6-35B-A3B-heretic-Q4_K_M-GGUF | image-text-to-text | 32GB - 48GB | 1,912 |
| Granddyser/BigLoveKlein-Collection | text-to-image | 8GB - 12GB | 1,912 |
| kai-os/Carnice-27b | text-generation | 32GB - 48GB | 1,909 |
| nvidia/audio-flamingo-next-hf | audio-text-to-text | 4GB - 8GB | 1,851 |
| Abiray/Huihui-Qwen3.6-35B-A3B-abliterated-GGUF | General | 32GB - 48GB | 1,848 |
| Rta-AILabs/Nandi-Mini-150M-Tool-Calling | text-generation | 8GB (Est.) * | 1,836 |
| DJLougen/Harmonic-Hermes-9B | text-generation | 8GB - 16GB | 1,835 |
| huihui-ai/Huihui-gemma-4-E2B-it-abliterated | any-to-any | 4GB - 8GB | 1,804 |
| Jackrong/Gemopus-4-26B-A4B-it | text-generation | 32GB - 48GB | 1,736 |
| google/timesfm-1.0-200m | time-series-forecasting | 8GB (Est.) * | 1,735 |
| GAIR/daVinci-MagiHuman | image-to-video | 8GB (Est.) * | 1,718 |
| FINAL-Bench/Darwin-35B-A3B-Opus | image-text-to-text | 32GB - 48GB | 1,695 |
| saricles/MiniMax-M2.7-NVFP4-GB10 | text-generation | 8GB (Est.) * | 1,684 |
| DJLougen/Ornstein3.6-35B-A3B-RYS-SABER | text-generation | 32GB - 48GB | 1,682 |
| Abiray/ERNIE-Image-Turbo-FP8-NVFP4 | text-to-image | 8GB - 12GB | 1,652 |
| miromind-ai/MiroThinker-1.7-mini | text-generation | 8GB (Est.) * | 1,630 |
| thetom-ai/MiniMax-M2.7-ConfigI-MLX | text-generation | 8GB (Est.) * | 1,629 |
| Comfy-Org/Gemma4 | General | 8GB (Est.) * | 1,621 |
| tencent/HY-Embodied-0.5 | image-text-to-text | 8GB (Est.) * | 1,599 |
| dx8152/Qwen-Image-Edit-2511-Gaussian-Splash | image-to-image | 8GB (Est.) * | 1,592 |
| dealignai/MiniMax-M2.7-JANG_3L-CRACK | text-generation | 8GB (Est.) * | 1,588 |
| NousResearch/Hermes-4-70B | text-generation | 64GB+ | 1,580 |
| 0xSero/Qwen3.5-264B-REAP-W4A16 | text-generation | 64GB+ | 1,558 |
| tencent/SongGeneration | text-to-audio | 4GB - 8GB | 1,490 |
| FunAudioLLM/Fun-ASR-Nano-2512 | General | 8GB (Est.) * | 1,465 |
| dealignai/MiniMax-M2.7-JANG_2L-CRACK | text-generation | 8GB (Est.) * | 1,464 |
| ArliAI/GLM-4.6-Derestricted-v3 | text-generation | 8GB (Est.) * | 1,462 |
| infly/Infinity-Parser2-Pro | General | 8GB (Est.) * | 1,430 |
| openbmb/VoxCPM-0.5B | text-to-speech | 8GB - 16GB | 1,421 |
| gguf-org/flux-dev-gguf | text-to-image | 8GB - 12GB | 1,379 |
| nvidia/magpie_tts_multilingual_357m | text-to-speech | 8GB (Est.) * | 1,367 |
| tencent/HunyuanVideo-1.5 | text-to-video | 8GB (Est.) * | 1,350 |
| rico03/Qwen3.6-35B-Opus-Reasoning-GGUF | text-generation | 32GB - 48GB | 1,334 |
| huihui-ai/Huihui-gemma-4-31B-it-abliterated-v2 | any-to-any | 32GB - 48GB | 1,331 |
| luffydenolan/Qwen3.6-35B-A3B-APEX-IQuality-GGUF | General | 32GB - 48GB | 1,321 |
| MediaTek-Research/Breeze-ASR-26 | automatic-speech-recognition | 8GB (Est.) * | 1,269 |
| llm-jp/llm-jp-4-vl-9b-beta | feature-extraction | 8GB - 16GB | 1,267 |
| Jackrong/MLX-Qwen3.5-9B-GLM5.1-Distill-v1-bf16 | text-generation | 8GB - 16GB | 1,267 |
| Zigeng/DMax-Coder-16B | text-generation | 32GB - 48GB | 1,261 |
| SicariusSicariiStuff/Assistant_Pepe_70B | General | 64GB+ | 1,225 |
| AIDC-AI/Marco-Mini-Instruct | text-generation | 8GB (Est.) * | 1,208 |
| tencent/HunyuanVideo | text-to-video | 8GB (Est.) * | 1,205 |
| DJLougen/Ornstein3.6-35B-A3B-RYS-SABER-GGUF | text-generation | 32GB - 48GB | 1,200 |
| FlashLabs/Chroma-4B | any-to-any | 8GB - 16GB | 1,189 |
| google/tipsv2-g14 | zero-shot-image-classification | 8GB (Est.) * | 1,182 |
| NucleusAI/Nucleus-Image | text-to-image | 8GB - 12GB | 1,179 |
| Jiunsong/supergemma4-e4b-abliterated-mlx | text-generation | 8GB - 16GB | 1,170 |
| dealignai/MiniMax-M2.7-JANGTQ-CRACK | text-generation | 8GB (Est.) * | 1,163 |
| Akira-Papa/akira-papa-1.0-e4b-jp | General | 8GB - 16GB | 1,154 |
| Jackrong/Qwen3.5-27B-GLM5.1-Distill-v1 | image-text-to-text | 32GB - 48GB | 1,145 |
| miromind-ai/MiroThinker-1.7 | text-generation | 8GB (Est.) * | 1,140 |
| llmfan46/gemma-4-26B-A4B-it-ultra-uncensored-heretic | image-text-to-text | 32GB - 48GB | 1,122 |
| DavidAU/gemma-4-19B-A4B-it-The-DECKARD-Heretic-Uncensored-Thinking | image-text-to-text | 32GB - 48GB | 1,090 |
| ginigen-ai/Rogue-27B-KR | text-generation | 32GB - 48GB | 1,078 |
| MJPansa/MiniMax-M2.7-REAP-172B-A10B-AutoRound-W4A16 | text-generation | 64GB+ | 1,063 |
| YTan2000/Gemma4-26b-Super-Abliterated-TQ3_4S | image-text-to-text | 32GB - 48GB | 1,055 |
| selimaktas/MiniMax-M2.75-460B-A20B | text-generation | 64GB+ | 1,049 |
| meituan-longcat/LongCat-Video | text-to-video | 8GB (Est.) * | 1,047 |
| tencent/HY-WorldPlay | image-to-video | 8GB (Est.) * | 1,016 |
| StentorLabs/Portimbria-150M | text-generation | 8GB (Est.) * | 1,011 |
| nvidia/nemotron-ocr-v2 | image-to-text | 8GB (Est.) * | 1,008 |
| coder3101/gemma-4-21b-a4b-it-REAP-heretic | text-generation | 32GB - 48GB | 1,005 |
| Jackrong/Gemopus-4-E4B-it | image-text-to-text | 8GB - 16GB | 995 |
| KRAFTON/Raon-SpeechChat-9B | audio-to-audio | 8GB - 16GB | 978 |
| arcinstitute/evo2_40b | General | 64GB+ | 968 |
| DJLougen/Ornstein-31B-it-GGUF | image-text-to-text | 32GB - 48GB | 967 |
| prism-ml/Ternary-Bonsai-1.7B-mlx-2bit | text-generation | 8GB - 16GB | 953 |
| Youssofal/MiniMax-M2.7-Abliterated-Heretic-MLX-4bit | text-generation | 8GB - 16GB | 949 |
| 0xSero/Qwen3.6-35B-A3B-GGUF-Strix | General | 32GB - 48GB | 943 |
| canberkkkkk/bs-vton-outfit-klein-9b | image-to-image | 8GB - 16GB | 942 |
| tvall43/Qwen3.6-35B-A3B-heretic | image-text-to-text | 32GB - 48GB | 913 |
| Jiunsong/supergemma4-e4b-abliterated | text-generation | 8GB - 16GB | 899 |
| LiquidAI/LFM2.5-Audio-1.5B | audio-to-audio | 8GB - 16GB | 895 |
| ibm-granite/granite-4.1-8b | General | 8GB - 16GB | 888 |
| hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF | text-generation | 32GB - 48GB | 867 |
| TeichAI/gemma-4-31B-it-Claude-Opus-Distill-v2 | image-text-to-text | 32GB - 48GB | 845 |
| sKT-Ai-Labs/SKT-SURYA-H | text-generation | 8GB (Est.) * | 836 |
| DJLougen/Ornstein-27B-SABER-RYS-GGUF | text-generation | 32GB - 48GB | 836 |
| ilkerzgi/face-swap | image-to-image | 8GB (Est.) * | 834 |
| Motif-Technologies/Motif-Video-2B | text-to-video | 4GB - 8GB | 824 |
| prism-ml/Ternary-Bonsai-4B-mlx-2bit | text-generation | 8GB - 16GB | 811 |
| yifanyu/I-DLM-32B | text-generation | 32GB - 48GB | 794 |
| saricles/MiniMax-M2.7-REAP-172B-A10B-NVFP4-GB10 | text-generation | 64GB+ | 787 |
| google/tipsv2-so400m14 | zero-shot-image-classification | 8GB (Est.) * | 770 |
| NidAll/supergemma4-e4b-abliterated-Q4_K_M-GGUF | text-generation | 8GB - 16GB | 760 |
| tencent/HY-Motion-1.0 | text-to-3d | 8GB (Est.) * | 754 |
| InsecureErasure/CyberRealisticXL-GGUF | text-to-image | 8GB - 12GB | 753 |
| ChenkinNoob/Chenkin-UniControl-XL | General | 8GB (Est.) * | 743 |
| z-lab/Kimi-K2.5-DFlash | text-generation | 8GB (Est.) * | 740 |
| advokat/AnimePro-FLUX | text-to-image | 8GB - 12GB | 739 |
| Minthy/ToriiGate-0.5 | image-text-to-text | 8GB (Est.) * | 737 |
| ZJU-AI4H/Hulu-Med-235A22 | image-text-to-text | 8GB (Est.) * | 733 |
| Brooooooklyn/Qwen3.6-35B-A3B-UD-Q4_K_XL-mlx | text-generation | 32GB - 48GB | 704 |
| DavidAU/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking | image-text-to-text | 64GB+ | 701 |
| nvidia/Kimodo-SOMA-RP-v1.1 | General | 8GB (Est.) * | 700 |
| tencent/Covo-Audio-Chat | audio-to-audio | 4GB - 8GB | 682 |
| DJLougen/Ornstein3.6-35B-A3B | text-generation | 32GB - 48GB | 674 |
| giants2026/GIANTS-4B | text-generation | 8GB - 16GB | 658 |
| loay/English-Document-OCR-Qwen3.5-0.8B | image-text-to-text | 8GB - 16GB | 642 |
| darkc0de/XortronCriminalComputingConfig | text-generation | 8GB (Est.) * | 639 |
| SandyResearch/parcae-1.3b | text-generation | 4GB - 8GB | 636 |
| tokinasin/llm-jp-4-8b-instruct-uncensored-ara | text-generation | 8GB - 16GB | 634 |
| KyleHessling1/Qwopus-GLM-18B-Merged-GGUF | text-generation | 32GB - 48GB | 632 |
| DeverStyle/Flux.2-Klein-Loras | text-to-image | 8GB - 12GB | 630 |
| FINAL-Bench/Darwin-4B-Genesis | text-generation | 8GB - 16GB | 628 |
| Jackrong/Qwopus3.5-27B-v3.5 | image-text-to-text | 32GB - 48GB | 628 |
| nvidia/EGM-4B | image-text-to-text | 8GB - 16GB | 628 |
| Alissonerdx/BFS-Best-Face-Swap-Video | image-to-video | 8GB (Est.) * | 615 |
| jedisct1/Qwen3.6-35B-rust.mlx | text-generation | 32GB - 48GB | 609 |
| nvidia/Ising-Calibration-1-35B-A3B | image-text-to-text | 32GB - 48GB | 593 |
| Video-Reason/VBVR-LTX2.3-diffsynth | image-to-video | 8GB (Est.) * | 584 |
| ServiceNow-AI/Apriel-1.6-15b-Thinker | image-text-to-text | 32GB - 48GB | 570 |
| Anzhc/Qwen2D-VAE | General | 8GB (Est.) * | 558 |
| huihui-ai/Huihui-GLM-5.1-abliterated-GGUF | text-generation | 8GB (Est.) * | 555 |
| dervig/m51Lab-MiniMax-M2.7-REAP-139B-A10B-NVFP4 | text-generation | 64GB+ | 555 |
| rocks20/task-21-Qwen-Qwen3.5-4B | text-generation | 8GB - 16GB | 541 |
| dealignai/Qwen3.5-VL-122B-A10B-4bit-MLX-CRACK-X | image-text-to-text | 64GB+ | 527 |
| huihui-ai/Huihui4-48B-A4B-abliterated | image-text-to-text | 64GB+ | 520 |
| caiovicentino1/Qwopus3.5-9B-v3-HLWQ-v7-GPTQ | text-generation | 8GB - 16GB | 516 |
| ggml-org/Qwen3.6-35B-A3B-GGUF | General | 32GB - 48GB | 507 |
| nvidia/audio-flamingo-next-captioner-hf | audio-text-to-text | 4GB - 8GB | 505 |
| RedHatAI/gemma-4-26B-A4B-it-speculator.eagle3 | General | 32GB - 48GB | 498 |
| knowledgator/gliner-x-large | token-classification | 8GB (Est.) * | 491 |
| nvidia/parakeet-unified-en-0.6b | automatic-speech-recognition | 8GB - 16GB | 487 |
| kai-os/gemma4-31b-Opus-4.6-reasoning | text-generation | 32GB - 48GB | 467 |
| Madras1/Qwen3-4b-Minimax-2.5-Reasoning-Distilled | text-generation | 8GB - 16GB | 457 |
| Ex0bit/MYTHOS-26B-A4B-PRISM-PRO-DQ-MLX | image-text-to-text | 4GB - 8GB | 443 |
| Youssofal/MiniMax-M2.7-abliterated-BF16 | text-generation | 8GB (Est.) * | 439 |
| Jackrong/Gemopus-4-31B-it | text-generation | 32GB - 48GB | 431 |
| TeichAI/gemma-4-26B-A4B-it-Claude-Opus-Distill-v2 | image-text-to-text | 32GB - 48GB | 430 |
| OpenMOSS-Team/MOSS-VL-Instruct-0408 | video-text-to-text | 8GB (Est.) * | 429 |
| aurateam/AURA | video-text-to-text | 8GB (Est.) * | 421 |
| OpenMOSS-Team/MOSS-Audio-8B-Thinking | audio-text-to-text | 8GB - 16GB | 409 |
| nothingiisreal/MN-12B-Celeste-V1.9 | text-generation | 32GB - 48GB | 405 |
| TendieLabs/Frank-26B-A4B | text-generation | 32GB - 48GB | 404 |
| huihui-ai/Huihui3.5-67B-A3B | image-text-to-text | 64GB+ | 404 |
| cturan/Olmo-3-7B-Instruct-Q1_0 | General | 8GB - 16GB | 402 |
| RingoSystems/RingoLLM | text-generation | 8GB (Est.) * | 385 |
| kyutai/ovie | image-to-image | 8GB (Est.) * | 379 |
| Jackrong/Qwopus3.5-9B-v3.5 | text-generation | 8GB - 16GB | 375 |
| pomazanbohdan/OmniCoder-9B-Strand-Rust-v1-GGUF | text-generation | 8GB - 16GB | 368 |
| OpenMOSS-Team/MOSS-Audio-4B-Instruct | audio-text-to-text | 8GB - 16GB | 356 |
| ArkAiLab-Adl/nexora-vector-v0.1 | text-generation | 8GB (Est.) * | 348 |
| wangzhang/Llama-3-8B-Instruct-DeepRefusal-Broken | text-generation | 8GB - 16GB | 347 |
| flwrlabs/Lizzy-7B | text-generation | 8GB - 16GB | 342 |
| AlicanKiraz0/Kizagan-E4B-Turkish-Reasoning-Model | text-generation | 8GB - 16GB | 334 |
| meituan-longcat/LongCat-Video-Avatar | General | 8GB (Est.) * | 324 |
| sphaela/Qwen3.6-35B-A3B-AutoRound-GGUF | General | 32GB - 48GB | 322 |
| tencent/POINTS-Seeker | text-generation | 8GB (Est.) * | 315 |
| RohitUltimate/Qwen3.5_VL_2B_12k | image-text-to-text | 4GB - 8GB | 305 |
| OBLITERATUS/Qwen3-4B-OBLITERATED | General | 8GB - 16GB | 291 |
| stepfun-ai/Step-Audio-R1.1 | audio-text-to-text | 4GB - 8GB | 278 |
| Goekdeniz-Guelmez/Josiefied-Qwen3.5-2B-gabliterated-v1 | text-generation | 4GB - 8GB | 276 |
| OpenMOSS-Team/MOSS-Audio-8B-Instruct | audio-text-to-text | 8GB - 16GB | 271 |
| jason1966/CoPaw-Flash-9B-DataAnalyst-LoRA | image-text-to-text | 8GB - 16GB | 256 |
| litert-community/functiongemma-270m-ft-mobile-actions | text-generation | 8GB (Est.) * | 252 |
| 0xSero/Qwen3.6-28B-REAP | text-generation | 32GB - 48GB | 250 |
| AviadDahan/LTX-2.3-ID-LoRA-TalkVid-3K | any-to-any | 8GB (Est.) * | 250 |
| prism-ml/Ternary-Bonsai-8B-unpacked | General | 8GB - 16GB | 246 |
| nvidia/EGM-8B | image-text-to-text | 8GB - 16GB | 235 |
| OpenMOSS-Team/MOSS-Audio-4B-Thinking | audio-text-to-text | 8GB - 16GB | 229 |
| ConicCat/Qwen3.5-27B-Writer-V2 | General | 32GB - 48GB | 223 |
| Ex0bit/MiniMax-SLURPY | text-generation | 4GB - 8GB | 213 |
| OrionLLM/GRM-2.5-Air | image-text-to-text | 8GB (Est.) * | 210 |
| huihui-ai/Huihui-Qwen3.6-35B-A3B-abliterated | image-text-to-text | 32GB - 48GB | 204 |
| google/tipsv2-g14-dpt | depth-estimation | 8GB (Est.) * | 203 |
| Skywork/Matrix-Game-3.0 | image-text-to-video | 8GB (Est.) * | 200 |
| OrionLLM/GRM-2.5 | image-text-to-text | 8GB (Est.) * | 184 |
| Max2475/Qwen3.5-9B-OpenSCAD-Instruct | text-generation | 8GB - 16GB | 172 |
| OpenMOSS-Team/moss-video-preview-realtime-sft | video-text-to-text | 8GB (Est.) * | 166 |
| llmfan46/Qwen3.6-35B-A3B-uncensored-heretic-GGUF | image-text-to-text | 32GB - 48GB | 164 |
| RohitUltimate/Qwen3.5_VL_2B_full_3 | image-text-to-text | 4GB - 8GB | 157 |
| wangzhang/Qwen3.6-35B-A3B-abliterated | General | 32GB - 48GB | 144 |
| AlicanKiraz0/Kizagan-E4B-Turkish-Reasoning-Model-Q8_0-GGUF | text-generation | 8GB - 16GB | 144 |
| allenai/WildDet3D | object-detection | 8GB (Est.) * | 143 |
| weya-ai/hush | audio-to-audio | 4GB - 8GB | 141 |
| Adilbai/stock-trading-rl-agent | reinforcement-learning | 8GB (Est.) * | 141 |
| hesamation/Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled | image-text-to-text | 32GB - 48GB | 138 |
| ChenkinNoob/ChenkinNoob-XL-V0.5 | text-to-image | 8GB - 12GB | 134 |
| nvidia/Lyra-2.0 | General | 8GB (Est.) * | 132 |
| tomaarsen/Qwen3-VL-Embedding-2B-vdr | visual-document-retrieval | 4GB - 8GB | 116 |
| FINAL-Bench/Darwin-TTS-1.7B-Cross | text-to-speech | 8GB - 16GB | 107 |
| EasonXiao-888/SpatialEdit-16B | image-text-to-image | 32GB - 48GB | 106 |
| webAI-Official/webAI-ColVec1-9b | visual-document-retrieval | 8GB - 16GB | 105 |
| SL-AI/GRaPE-2-Mini | image-text-to-text | 8GB (Est.) * | 101 |
| nvidia/UniRelight | General | 8GB (Est.) * | 98 |
| OpenMOSS-Team/moss-video-preview-base | video-text-to-text | 8GB (Est.) * | 98 |
| RedHatAI/gemma-4-31B-it-speculator.dflash | General | 32GB - 48GB | 95 |
| WithinUsAI/Opus4.7-GODsGhostCodex-4B.GGUF | text-generation | 8GB - 16GB | 92 |
| OpenMOSS-Team/MOSS-VL-Base-0408 | video-text-to-text | 8GB (Est.) * | 86 |
| knowledgator/gliner-relex-multi-v1.0 | token-classification | 8GB (Est.) * | 84 |
| kandinskylab/KVAE-3D-2.0-t4s16 | General | 8GB (Est.) * | 83 |
| FINAL-Bench/Darwin-27B-Opus | text-generation | 32GB - 48GB | 80 |
| artefactory/BERTJudge | text-classification | 8GB (Est.) * | 73 |
| nvidia/PixelDiT-1300M-1024px | text-to-image | 8GB - 12GB | 72 |
| mratsim/Qwen3.5-397B-A17B-EXL3 | image-text-to-text | 64GB+ | 71 |
| wangzhang/gemma-4-26B-A4B-it-abliterix | General | 32GB - 48GB | 67 |
| nvidia/Lyra | General | 8GB (Est.) * | 67 |
| kyutai/moshika-rag-candle-bf16 | audio-to-audio | 4GB - 8GB | 67 |
| kandinskylab/KVAE-3D-2.0-t4s8 | General | 8GB (Est.) * | 66 |
| saadxsalman/SS-Talk-2-Bash | text-generation | 8GB (Est.) * | 64 |
| limuloo1999/RefineAnything | General | 8GB (Est.) * | 61 |
| TIGER-Lab/RationalRewards-8B-T2I | image-to-text | 8GB - 16GB | 54 |
| zerofata/G4-MeroMero-26B-A4B | General | 32GB - 48GB | 50 |
| MrReclusive/LTX-2.3-FP4 | image-to-video | 8GB (Est.) * | 49 |
| SL-AI/GRaPE-2-Flash | image-text-to-text | 8GB (Est.) * | 43 |
| Alibaba-DAMO-Academy/RynnBrain-4B | image-text-to-text | 8GB - 16GB | 41 |
| ApacheOne/ERNIE-Image-nvfp4_mixed | General | 8GB (Est.) * | 35 |
| FreedomIntelligence/HuatuoGPT-3-32B | text-generation | 32GB - 48GB | 35 |
| WhaletechAI/W1-4B-dLLM-Base | General | 8GB - 16GB | 32 |
| FreedomIntelligence/HuatuoGPT-3-8B | text-generation | 8GB - 16GB | 26 |
| Writer/Palmyra-Creative | General | 8GB (Est.) * | 25 |
| tencent/Unified_Audio_Schema | audio-text-to-text | 4GB - 8GB | 18 |
| dida-80b/kokoro-german-hui-multispeaker-base | text-to-speech | 64GB+ | 11 |
| tencent/HY-World-2.0 | image-to-3d | 8GB (Est.) * | 0 |
| Comfy-Org/ERNIE-Image | General | 8GB (Est.) * | 0 |
| netflix/void-model | video-to-video | 8GB (Est.) * | 0 |
| robbyant/lingbot-map | General | 8GB (Est.) * | 0 |
| RuneXX/LTX-2.3-Workflows | image-to-video | 8GB (Est.) * | 0 |
| Alissonerdx/LTX-LoRAs | General | 8GB (Est.) * | 0 |
| oumoumad/LTX-2.3-22b-IC-LoRA-Outpaint | video-to-video | 32GB - 48GB | 0 |
| Phr00t/Qwen-Image-Edit-Rapid-AIO | text-to-image | 8GB - 12GB | 0 |
| lrzjason/Consistance_Edit_Lora | General | 8GB (Est.) * | 0 |
| HKUSTAudio/Audio-Omni | any-to-any | 8GB (Est.) * | 0 |
| obsxrver/wan2.2-i2v-lightx2v-260412 | General | 8GB (Est.) * | 0 |
| microsoft/TRELLIS.2-4B | image-to-3d | 8GB - 16GB | 0 |
| lkzd7/WAN2.2_LoraSet_NSFW | General | 8GB (Est.) * | 0 |
| Phr00t/WAN2.2-14B-Rapid-AllInOne | image-to-video | 32GB - 48GB | 0 |
| Comfy-Org/sam3.1 | General | 8GB (Est.) * | 0 |
| duongve/AnimaYume | text-to-image | 8GB - 12GB | 0 |
| Aratako/Irodori-TTS-500M-v2 | text-to-speech | 8GB (Est.) * | 0 |
| nvidia/Ising-Decoder-SurfaceCode-1-Fast | General | 8GB (Est.) * | 0 |
| tencent/DisCa | General | 8GB (Est.) * | 0 |
| Aratako/Irodori-TTS-500M-v2-VoiceDesign | text-to-speech | 8GB (Est.) * | 0 |
| VAST-AI/AniGen | image-to-3d | 8GB (Est.) * | 0 |
| facebook/boxer | object-detection | 8GB (Est.) * | 0 |
| rhasspy/piper-voices | General | 8GB (Est.) * | 0 |
| Comfy-Org/vae-text-encorder-for-flux-klein-9b | General | 8GB - 16GB | 0 |
| Lightricks/LTX-2.3-22b-IC-LoRA-Union-Control | any-to-any | 32GB - 48GB | 0 |
| RoyalCities/Foundation-1 | General | 8GB (Est.) * | 0 |
| ggerganov/whisper.cpp | automatic-speech-recognition | 8GB (Est.) * | 0 |
| ResembleAI/chatterbox-turbo | text-to-speech | 8GB (Est.) * | 0 |
| Lightricks/LTX-2-19b-IC-LoRA-Detailer | video-to-video | 32GB - 48GB | 0 |
| nvidia/GEAR-SONIC | reinforcement-learning | 8GB (Est.) * | 0 |
| Aratako/Irodori-TTS-500M | text-to-speech | 8GB (Est.) * | 0 |
| Cseti/LTX2.3-22B_IC-LoRA-Cameraman_v1 | General | 32GB - 48GB | 0 |
| GuangyuanSD/ErnieTurbo_extracted_lora | General | 8GB (Est.) * | 0 |
| mni-ml/transformer | text-generation | 8GB (Est.) * | 0 |
| lllyasviel/ControlNet-v1-1 | General | 8GB (Est.) * | 0 |
| inspatio/world | General | 8GB (Est.) * | 0 |
| lodestones/tagger-experiment | image-classification | 8GB (Est.) * | 0 |
| tencent/HY-OmniWeaving | image-to-video | 8GB (Est.) * | 0 |
| nvidia/Ising-Decoder-SurfaceCode-1-Accurate | General | 8GB (Est.) * | 0 |
| CompVis/myriad | other | 8GB (Est.) * | 0 |
| drbaph/Woosh | text-to-audio | 4GB - 8GB | 0 |
| CompVis/ZipMo | image-to-video | 8GB (Est.) * | 0 |
| dummy9996/ERNIE-Image-fp8 | General | 8GB (Est.) * | 0 |
| Intel/Qwen3.6-35B-A3B-int4-AutoRound | General | 32GB - 48GB | 0 |
| lllyasviel/sd_control_collection | General | 8GB (Est.) * | 0 |
| Kim2091/UltraSharpV2 | image-to-image | 8GB (Est.) * | 0 |
| pipecat-ai/smart-turn-v3 | voice-activity-detection | 8GB (Est.) * | 0 |
| lodestones/Zeta-Chroma | text-to-image | 8GB - 12GB | 0 |
| cyrildiagne/flux2-klein9b-lora-mlsharp-3d-repair | General | 8GB - 16GB | 0 |
| F16/z-image-turbo-flow-dpo | feature-extraction | 2GB - 4GB | 0 |
| jonpai/mimic-video | General | 8GB (Est.) * | 0 |
| lylogummy/anima2b-qwen-3.5-4b | General | 4GB - 8GB | 0 |
| Winnougan/Must_Have_Klein_9b_loras | text-to-image | 8GB - 16GB | 0 |
| well9472/Nanosaur-1.2B-Preview | General | 4GB - 8GB | 0 |
| dx8152/LTX2.3-Multifunctional | text-to-video | 8GB (Est.) * | 0 |
| mirror-physics/equiformer_v3 | graph-ml | 8GB (Est.) * | 0 |
| o-8-o/LTX-2.3-skin-hair | General | 8GB (Est.) * | 0 |
| bytedance-research/GRN | General | 8GB (Est.) * | 0 |
| ai-forever/Real-ESRGAN | General | 8GB (Est.) * | 0 |
| TMElyralab/MuseTalk | General | 8GB (Est.) * | 0 |
| myshell-ai/OpenVoiceV2 | text-to-speech | 8GB (Est.) * | 0 |
| comfyanonymous/flux_text_encoders | General | 8GB (Est.) * | 0 |
| sphiratrioth666/SillyTavern-Presets-Sphiratrioth | General | 8GB (Est.) * | 0 |
| BlinkDL/rwkv7-g1 | text-generation | 8GB (Est.) * | 0 |
| ACE-Step/ACE-Step-v1-3.5B | text-to-audio | 8GB - 16GB | 0 |
| Heartsync/Flux-NSFW-uncensored | text-to-image | 8GB - 12GB | 0 |
| kyutai/tts-voices | General | 8GB (Est.) * | 0 |
| jarredou/BS-ROFO-SW-Fixed | General | 8GB (Est.) * | 0 |
| xororz/sd-qnn | General | 8GB (Est.) * | 0 |
| 1038lab/sam3 | mask-generation | 8GB (Est.) * | 0 |
| huaichang/PersonaLive | image-to-video | 8GB (Est.) * | 0 |
| Comfy-Org/ltx-2 | General | 8GB (Est.) * | 0 |
| Comfy-Org/vae-text-encorder-for-flux-klein-4b | General | 8GB - 16GB | 0 |
| Sikaworld1990/gemma-3-12b-it-abliterated-sikaworld-high-fidelity-edition-Ltx-2 | General | 32GB - 48GB | 0 |
| MIUProject/VNCCS_PoseStudio | General | 8GB (Est.) * | 0 |
| Sentinel7/flux2 | General | 8GB (Est.) * | 0 |
| ussoewwin/Sage-Attention-for-Windows | General | 8GB (Est.) * | 0 |
| Starnodes/quants | General | 8GB (Est.) * | 0 |
| nikopueringer/CorridorKey_v1.0 | mask-generation | 8GB (Est.) * | 0 |
| facebook/EUPE-ViT-B | General | 8GB (Est.) * | 0 |
| tventurella/mr_chatterbox_model | General | 8GB (Est.) * | 0 |
| aifeifei798/Mamba3-MIMO-Tiny-HF | text-generation | 8GB (Est.) * | 0 |
| Comfy-Org/frame_interpolation | General | 8GB (Est.) * | 0 |
| nvidia/nemocurator-speech-bandwidth-filter | General | 8GB (Est.) * | 0 |
Want a real-time scan? Visit our interactive checker