| 1 | Qwen2.5-3B-Instructunsloth | Text Generation | 4,996 | +4,996 | 17 | 3.1B |
| 2 | tiny-random-phi-4-multimodaloptimum-intel-internal-testing | Image Text to Text | 4,995 | +4,995 | 0 | 6.5M |
| 3 | Magistral-Small-2509-MLX-4bitlmstudio-community | — | 4,993 | +4,993 | 0 | — |
| 4 | tiny-random-llama4optimum-intel-internal-testing | Image Text to Text | 4,991 | +4,991 | 0 | 6.6M |
| 5 | qwen3-asr-cs-1.7binferRouter | Speech Recognition | 4,990 | +4,990 | 2 | 2B |
| 6 | FLUX.1-dev-Controlnet-UnionInstantX | — | 4,990 | +4,990 | 488 | 3.3B |
| 7 | convnext_large.fb_in22k_ft_in1ktimm | Image Classification | 4,989 | +4,989 | 3 | 198M |
| 8 | swiftformer-xsMBZUAI | Image Classification | 4,987 | +4,987 | 8 | 3.5M |
| 9 | koelectra-base-v3-naver-nermonologg | Token Classification | 4,985 | +4,985 | 11 | — |
| 10 | OpenMed-ZeroShot-NER-Anatomy-Large-459MOpenMed | Token Classification | 4,983 | +4,983 | 0 | — |
| 11 | testllmlovis93 | Text to Image | 4,980 | +4,980 | 13 | 11.9B |
| 12 | kanana-1.5-v-3b-instructkakaocorp | Image Text to Text | 4,980 | +4,980 | 56 | 3.7B |
| 13 | small-agentic-model-1.5Bjoaosollatori | Text Generation | 4,979 | +4,979 | 1 | 124M |
| 14 | musicgen-melodyfacebook | Text to Audio | 4,978 | +4,978 | 262 | 1.6B |
| 15 | YOLO11Ultralytics | Object Detection | 4,978 | +4,978 | 207 | — |
| 16 | speaker-diarization-coremlFluidInference | Voice Activity Detection | 4,973 | +4,973 | 43 | — |
| 17 | tiny-lmsbintuitions | Text Generation | 4,969 | +4,969 | 2 | — |
| 18 | OLMoE-1B-7B-0924-Instructallenai | Text Generation | 4,965 | +4,965 | 100 | 6.9B |
| 19 | micro-g3.3-8b-instruct-1bibm-ai-platform | — | 4,962 | +4,962 | 6 | 1.2B |
| 20 | K2-Horizon-7B-GGUFIFM | Text Generation | 4,962 | +4,962 | 76 | — |
| 21 | NTv3_650M_preInstaDeepAI | Fill Mask | 4,961 | +4,961 | 8 | 652M |
| 22 | zai-org.GLM-5.3-Flash-GGUFDevQuasar | Text Generation | 4,954 | +4,954 | 10 | — |
| 23 | Qwen3.5-9B-Cold-Fusion-GAIN-v1.0-Uncensored-Heretic-NEO-MAX-Imatrix-GGUFDavidAU | Image Text to Text | 4,954 | +4,954 | 33 | — |
| 24 | InternVL3_5-4B-HFOpenGVLab | Image Text to Text | 4,950 | +4,950 | 6 | 4.7B |
| 25 | deepseek-vl-7b-chatdeepseek-community | Image Text to Text | 4,948 | +4,948 | 2 | 7.3B |
| 26 | geo-all-MiniLM-L6-v2dguzh | Sentence Similarity | 4,947 | +4,947 | 0 | 22.7M |
| 27 | granite-3.0-1b-a400m-baseibm-granite | Text Generation | 4,945 | +4,945 | 7 | 1.4B |
| 28 | DeepSeek-R1-0528-NVFP4-v2nvidia | Text Generation | 4,942 | +4,942 | 23 | 394B |
| 29 | MedEmbed-small-v0.1abhinand | — | 4,942 | +4,942 | 24 | 33.4M |
| 30 | msmarco-MiniLM-L6-en-de-v1cross-encoder | Text Ranking | 4,939 | +4,939 | 14 | 107M |
| 31 | NeoHorse-1-9BTokenRhythm | Text Generation | 4,935 | +4,935 | 1,023 | 9B |
| 32 | whisper-tiny.en_timestampedonnx-community | Speech Recognition | 4,934 | +4,934 | 1 | — |
| 33 | F2LLM-v2-80Mcodefuse-ai | Embeddings | 4,934 | +4,934 | 16 | 80.1M |
| 34 | UNSEEN_Gemma_4_26B_NSFW-GGUFJommarn | Image Text to Text | 4,931 | +4,931 | 96 | — |
| 35 | vilt-b32-mlmdandelin | Fill Mask | 4,928 | +4,928 | 13 | — |
| 36 | Magistral-Small-2509-MLX-5bitlmstudio-community | — | 4,927 | +4,927 | 0 | — |
| 37 | metricx-24-hybrid-xxl-v2p6-bfloat16google | — | 4,926 | +4,926 | 7 | — |
| 38 | OpenMed-ZeroShot-NER-Oncology-Tiny-60MOpenMed | Token Classification | 4,925 | +4,925 | 0 | — |
| 39 | ERNIE-4.5-21B-A3B-PTbaidu | Text Generation | 4,925 | +4,925 | 178 | 21.9B |
| 40 | gollem-v4-250m-plSlayerLab | Text Generation | 4,924 | +4,924 | 4 | — |
| 41 | TinyLlama-1.1B-Chat-v1.0-llamafilemozilla-ai | — | 4,922 | +4,922 | 16 | — |
| 42 | Ornith-1.5-9B-MTP-GGUFprotoLabsAI | Image Text to Text | 4,922 | +4,922 | 39 | — |
| 43 | Qwen3.8-27B-AEON-ULTIMATE-UNCENSORED-NVFP4-MIXEDAEON-7 | Text Generation | 4,919 | +4,919 | 45 | 19.9B |
| 44 | Magistral-Small-2509-MLX-6bitlmstudio-community | — | 4,919 | +4,919 | 0 | — |
| 45 | bge-small-en-MNNdarkmaniac7 | Embeddings | 4,916 | +4,916 | 0 | — |
| 46 | mobilenet_v1_1.0_224google | Image Classification | 4,916 | +4,916 | 1 | — |
| 47 | stable-audio-3-small-musicstabilityai | Text to Audio | 4,912 | +4,912 | 179 | 568M |
| 48 | Llama-3.1-Nemotron-70B-Instruct-HFnvidia | Text Generation | 4,910 | +4,910 | 2,070 | 70.6B |
| 49 | Dolphin3.0-Llama3.1-8B-GGUFbartowski | Text Generation | 4,904 | +4,904 | 33 | — |
| 50 | Llama-3.2-3B-TechWriter-Instruct-UnslothShankarblr | Text Generation | 4,903 | +4,903 | 1 | 3.2B |