| 1 | mask2former-swin-tiny-cityscapes-semanticfacebook | Image Segmentation | 1,584 | +1,584 | 4 | 47.4M |
| 2 | fastspeech2_conformer_with_hifiganespnet | Text to Audio | 1,583 | +1,583 | 1 | — |
| 3 | DeepSeek-V3-debug-empty-FP8_DYNAMICinference-optimization | — | 1,583 | +1,583 | 0 | 1.3B |
| 4 | Artemis-31B-v1.1-GGUFTheDrummer | — | 1,583 | +1,583 | 32 | — |
| 5 | feel-it-italian-sentimentMilaNLProc | Text Classification | 1,583 | +1,583 | 22 | — |
| 6 | cookgptlamaVishalMysore | Text Generation | 1,581 | +1,581 | 3 | 1.1B |
| 7 | animatediff-motion-adapter-v1-5-3guoyww | Text to Video | 1,581 | +1,581 | 11 | 418M |
| 8 | LTX-2.5-Comfy-GGUFruygar | Text to Video | 1,581 | +1,581 | 12 | — |
| 9 | Revisual-R1-Coldstart-i1-GGUFmradermacher | — | 1,581 | +1,581 | 0 | — |
| 10 | uform3-image-text-multilingual-baseunum-cloud | Embeddings | 1,580 | +1,580 | 17 | — |
| 11 | SmolLM2-135M-GGUFQuantFactory | — | 1,580 | +1,580 | 4 | — |
| 12 | faster-distil-whisper-medium.enSystran | Speech Recognition | 1,579 | +1,579 | 4 | — |
| 13 | flux.1-dev-uncensored-q4windylight | — | 1,579 | +1,579 | 0 | 6.1B |
| 14 | LongCat-Flash-Lite-FP8meituan-longcat | Text Generation | 1,578 | +1,578 | 9 | 69.1B |
| 15 | TheDrummer_Valkyrie-49B-v2.1-GGUFbartowski | Text Generation | 1,578 | +1,578 | 10 | — |
| 16 | falcon-rw-1btiiuae | Text Generation | 1,578 | +1,578 | 119 | — |
| 17 | jinen-v1-xsmall.gguftogatogah | — | 1,578 | +1,578 | 1 | — |
| 18 | Devstral-2-123B-Instruct-2512-GGUFunsloth | — | 1,578 | +1,578 | 57 | — |
| 19 | moody-porn-mix-v10-dpo-ggufGthalmie1 | Text to Image | 1,577 | +1,577 | 16 | — |
| 20 | dolphin-2.9-llama3-8b-ggufdphn | — | 1,577 | +1,577 | 93 | — |
| 21 | Chronos-Divergence-33B-GGUFbartowski | Text Generation | 1,577 | +1,577 | 3 | — |
| 22 | Qwen2.5-32B-i1-GGUFmradermacher | — | 1,576 | +1,576 | 0 | — |
| 23 | guwenbert-baseethanyt | Fill Mask | 1,575 | +1,575 | 25 | — |
| 24 | 2023_Scraped_SDXLMLbackup | Text to Image | 1,574 | +1,574 | 4 | — |
| 25 | Qwen3-Zero-Coder-Reasoning-0.8B-NEO-EX-GGUFDavidAU | Text Generation | 1,574 | +1,574 | 28 | — |
| 26 | Swift-Qwen3.8-27B-Uncensored-MTP-GGUFmradermacher | — | 1,574 | +1,574 | 2 | — |
| 27 | SearchR1-nq_hotpotqa_train-qwen2.5-7b-it-em-ppoPeterJinGo | — | 1,574 | +1,574 | 0 | 7.6B |
| 28 | starcoder2-15b-instruct-v0.1-GGUFbartowski | Text Generation | 1,573 | +1,573 | 9 | — |
| 29 | grammar_error_correcter_v1prithivida | — | 1,573 | +1,573 | 41 | — |
| 30 | Qwen-Image-2512-Turbo-LoRAWuli-art | Text to Image | 1,573 | +1,573 | 227 | — |
| 31 | Qwen2.5-7B-unsloth-bnb-4bitunsloth | Text Generation | 1,573 | +1,573 | 1 | 7.8B |
| 32 | seresnext26d_32x4d.bt_in1ktimm | Image Classification | 1,572 | +1,572 | 0 | 16.8M |
| 33 | LLM2Vec-Mistral-7B-Instruct-v2-mntp-unsup-simcseMcGill-NLP | Sentence Similarity | 1,572 | +1,572 | 7 | — |
| 34 | Florence-2-large-no-flash-attnmultimodalart | Image Text to Text | 1,572 | +1,572 | 26 | — |
| 35 | Tifa-DeepsexV2-7b-MGRPO-GGUF-Q4ValueFX9507 | Reinforcement Learning | 1,571 | +1,571 | 230 | — |
| 36 | refcontrol-FLUX.2-klein-9B-reference-depth-lorathedeoxen | Image To Image | 1,571 | +1,571 | 79 | — |
| 37 | ScreenHighlighterRL-2B-i1-GGUFmradermacher | Reinforcement Learning | 1,570 | +1,570 | 0 | — |
| 38 | nemotron-colembed-vl-4b-v2nvidia | Visual Document Retrieval | 1,570 | +1,570 | 38 | 4.8B |
| 39 | OctoThinker-8B-Long-Base-GGUFtinyopsec | Text Generation | 1,569 | +1,569 | 0 | — |
| 40 | Nous-Hermes-13B-Code-GGUFTheBloke | — | 1,569 | +1,569 | 11 | — |
| 41 | hayai-ocr-v2JustANormalTinkerer | Image to Text | 1,569 | +1,569 | 8 | 156M |
| 42 | Hermes-3-Llama-3.2-3B-GGUFNousResearch | — | 1,568 | +1,568 | 76 | — |
| 43 | LFM2.5-2.6B-Pashto-Zinassimjp | Text Generation | 1,568 | +1,568 | 1 | 2.7B |
| 44 | mistralai_Mistral-Medium-3.5-128B-GGUFbartowski | Image Text to Text | 1,567 | +1,567 | 10 | — |
| 45 | PhotoMakerTencentARC | Text to Image | 1,567 | +1,567 | 438 | — |
| 46 | CLIP-ViT-H-14-laion2B-s32B-b79K_repackagedComfy-Org | — | 1,567 | +1,567 | 5 | — |
| 47 | Hermes-2.5-Yi-1.5-9B-Chat-i1-GGUFmradermacher | — | 1,567 | +1,567 | 0 | — |
| 48 | waiIllustriousSDXL_v170frankjoshua | Text to Image | 1,566 | +1,566 | 0 | 2.6B |
| 49 | bert-base-multilingual-cased-language-detectionjb2k | Text Classification | 1,566 | +1,566 | 14 | — |
| 50 | moondream2-ggufmoondream | — | 1,565 | +1,565 | 40 | — |