| 1 | coco_panoptic_eomt_large_640tue-mps | Image Segmentation | 15K | +15K | 14 | 317M |
| 2 | Qwen3-VL-8B-Instruct-GGUFunsloth | Image Text to Text | 15K | +15K | 94 | — |
| 3 | Qwen3-Coder-30B-A3B-Instruct-4bitmlx-community | Text Generation | 15K | +15K | 46 | 30.5B |
| 4 | DA3-LARGEdepth-anything | Depth Estimation | 15K | +15K | 16 | 411M |
| 5 | colqwen2-v1.0vidore | Visual Document Retrieval | 15K | +15K | 121 | — |
| 6 | DeepSeek-R1-0528-Qwen3-8B-GGUFunsloth | Text Generation | 15K | +15K | 464 | — |
| 7 | Qianfan-OCRbaidu | Image Text to Text | 14.9K | +14.9K | 1,205 | 4.7B |
| 8 | Qwen3-4B-unsloth-bnb-4bitunsloth | Text Generation | 14.9K | +14.9K | 21 | 4.1B |
| 9 | Llama-3.2-1B-Instruct-Q4_K_M-GGUFhugging-quants | Text Generation | 14.9K | +14.9K | 33 | — |
| 10 | whisper-large-v3-FP8-dynamicRedHatAI | Speech Recognition | 14.9K | +14.9K | 5 | 1.6B |
| 11 | vit_large_patch14_clip_336.openaitimm | Zero-Shot Image Classification | 14.9K | +14.9K | 2 | 304M |
| 12 | tiny-Phi3ForCausalLMtrl-internal-testing | Text Generation | 14.8K | +14.8K | 0 | 514.1K |
| 13 | tiny-random-Phi3ForCausalLMoptimum-intel-internal-testing | Text Generation | 14.8K | +14.8K | 0 | 2.1M |
| 14 | DA3-SMALLdepth-anything | Depth Estimation | 14.8K | +14.8K | 23 | 34.3M |
| 15 | granite-4.2-3bibm-granite | Text Generation | 14.8K | +14.8K | 111 | 3.7B |
| 16 | deberta-v3-base-zeroshot-v2.0MoritzLaurer | Zero-Shot Classification | 14.8K | +14.8K | 18 | 184M |
| 17 | Qwen3-VL-8B-Instruct-GGUFlmstudio-community | — | 14.8K | +14.8K | 6 | — |
| 18 | bekko-embedding-v1-a25mhotchpotch | Sentence Similarity | 14.8K | +14.8K | 32 | 123M |
| 19 | tiny-random-z-imageoptimum-intel-internal-testing | Text to Image | 14.8K | +14.8K | 0 | 706.1K |
| 20 | Qwen3-4B-Thinking-2507-GGUFMaziyarPanahi | Text Generation | 14.8K | +14.8K | 2 | — |
| 21 | DiffuRefill-1BAsilarkness | Text Generation | 14.8K | +14.8K | 3 | — |
| 22 | prompt-guard-68msheltron-ai | Text Classification | 14.8K | +14.8K | 4 | 68.4M |
| 23 | Cosmos-Predict2-2B-Video2Worldnvidia | Image To Video | 14.8K | +14.8K | 106 | — |
| 24 | Wan2.1-I2V-14B-480PWan-AI | Image To Video | 14.8K | +14.8K | 238 | 16.4B |
| 25 | Qwopus3.8-27B-Flash-GGUFJackrong | Image Text to Text | 14.8K | +14.8K | 245 | — |
| 26 | Qwen3.8-27B-AWQ-INT4avyukth | Image Text to Text | 14.8K | +14.8K | 4 | 27.4B |
| 27 | dvine82-xlmartineux | Text to Image | 14.8K | +14.8K | 0 | 2.6B |
| 28 | tiny-random-pegasusoptimum-intel-internal-testing | — | 14.7K | +14.7K | 0 | — |
| 29 | CodeLlama-7b-Instruct-hfcodellama | Text Generation | 14.7K | +14.7K | 260 | 6.7B |
| 30 | gliner_multi_pii-v1urchade | Token Classification | 14.7K | +14.7K | 177 | — |
| 31 | Ace-Step1.5ACE-Step | Text to Audio | 14.7K | +14.7K | 894 | — |
| 32 | DeepSeek-R1-Distill-Qwen-1.5Blitert-community | Text Generation | 14.7K | +14.7K | 54 | — |
| 33 | BGE-m3-kodragonkue | Sentence Similarity | 14.7K | +14.7K | 77 | 568M |
| 34 | tiny-random-phi3katuni4ka | Text Generation | 14.7K | +14.7K | 0 | 3.1M |
| 35 | GLM-OCRunsloth | Image to Text | 14.7K | +14.7K | 37 | 1.3B |
| 36 | ViT-B-16-SigLIP2timm | Zero-Shot Image Classification | 14.7K | +14.7K | 1 | — |
| 37 | Rocinante-XL-16B-v1-GGUFTheDrummer | — | 14.7K | +14.7K | 37 | — |
| 38 | nli-deberta-v3-xsmallcross-encoder | Zero-Shot Classification | 14.6K | +14.6K | 7 | 70.8M |
| 39 | canary-qwen-2.5b-ggufhandy-computer | Speech Recognition | 14.6K | +14.6K | 1 | — |
| 40 | Qwen2.5-VL-32B-Instruct-AWQQwen | Image Text to Text | 14.6K | +14.6K | 66 | 33.5B |
| 41 | Qwen-Image-Edit-2509-Photo-to-Animeautoweeb | Image To Image | 14.6K | +14.6K | 132 | — |
| 42 | bros-base-uncasednaver-clova-ocr | Embeddings | 14.6K | +14.6K | 19 | — |
| 43 | Qwen2.5-Coder-32B-Instruct-MLX-8bitlmstudio-community | Text Generation | 14.6K | +14.6K | 4 | 32.8B |
| 44 | Qwen3.8-27B-ABLITERATED-NVFP4Blackfrost-AI | Image Text to Text | 14.6K | +14.6K | 16 | 18.5B |
| 45 | Qwen2.5-0.5B-Instruct-q4f16_1-MLCmlc-ai | — | 14.6K | +14.6K | 4 | — |
| 46 | Olmo-3-7B-Thinkallenai | Text Generation | 14.6K | +14.6K | 109 | 7.3B |
| 47 | opus-mt-fr-esHelsinki-NLP | Translation | 14.6K | +14.6K | 1 | — |
| 48 | roberta-spanish-sentiment-analysisUMUTeam | Text Classification | 14.5K | +14.5K | 2 | 125M |
| 49 | tiny-random-BartForConditionalGenerationpeft-internal-testing | — | 14.5K | +14.5K | 0 | 28.2K |
| 50 | Qwen3-VL-235B-A22B-Instruct-FP8Qwen | Image Text to Text | 14.5K | +14.5K | 47 | 236B |