1,054 models · refreshed nightly
All models
Every model in the catalog with its licence, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 51 | Ornith-1.5-9B-GGUF | — | — | ✓ mit | 5.8 M | from 6.9 GB |
| 52 | Qwen3.6-27B-FP8 | 27.8 B | — | ✓ apache-2.0 | 5.8 M | from 38.6 GB |
| 53 | speaker-diarization-community-1 | — | — | ✓ cc-by-4.0 | 5.3 M | — |
| 54 | finbert | — | 512 | unknown | 5.3 M | — |
| 55 | gpt-oss-120b | 120.4 B | 131 K | ✓ apache-2.0 | 5.1 M | from 162.1 GB |
| 56 | bge-small-zh-v1.5 | 20 M | 512 | ✓ mit | 5.1 M | from 0.6 GB |
| 57 | Qwen2.5-3B-Instruct | 3.1 B | 33 K | other | 5.1 M | from 7.8 GB |
| 58 | Qwen3-32B | 32.8 B | 41 K | ✓ apache-2.0 | 5.0 M | from 77.5 GB |
| 59 | Ornith-1.0-9B-GGUF | — | — | ✓ mit | 4.9 M | from 6.7 GB |
| 60 | dolphin-2.9.1-yi-1.5-34b | 34.4 B | 8 K | ✓ apache-2.0 | 4.8 M | from 81.3 GB |
| 61 | Qwen3.5-2B | 2.3 B | — | ✓ apache-2.0 | 4.8 M | from 5.8 GB |
| 62 | Qwen3.8-27B-MLX-4bit | 4.7 B | — | ✓ apache-2.0 | 4.7 M | from 18.9 GB |
| 63 | whisper-large-v3 | 1.5 B | — | ✓ apache-2.0 | 4.7 M | from 10.9 GB |
| 64 | Ornith-1.5-35B-A3B-GGUF | — | — | ✓ mit | 4.6 M | from 24.4 GB |
| 65 | Qwen3.8-27B-MLX-8bit | 8.0 B | — | ✓ apache-2.0 | 4.5 M | from 34.2 GB |
| 66 | Qwen3.8-27B-MLX-6bit | 6.4 B | — | ✓ apache-2.0 | 4.5 M | from 26.5 GB |
| 67 | Qwen3.8-27B-MLX-5bit | 5.5 B | — | ✓ apache-2.0 | 4.5 M | from 22.7 GB |
| 68 | Prompt-Guard-86M | 280 M | — | ⚠ llama3.1 | 4.4 M | from 1.8 GB |
| 69 | audio.cpp-gguf | — | — | other | 4.3 M | from 1.4 GB |
| 70 | bge-base-en-v1.5-course-recommender-v5 | 110 M | 512 | unknown | 4.2 M | from 1.0 GB |
| 71 | all-MiniLM-L12-v2 | 30 M | 512 | ✓ apache-2.0 | 4.2 M | from 0.7 GB |
| 72 | DeepSeek-V4-Flash-0731 | 304.2 B | 1.0 M | ✓ mit | 4.2 M | from 229.7 GB |
| 73 | wav2vec2-large-xlsr-53-russian | — | — | ✓ apache-2.0 | 4.2 M | — |
| 74 | Qwen-72B | 72.3 B | 33 K | other | 4.2 M | from 170.4 GB |
| 75 | bge-reranker-base | 280 M | 512 | ✓ mit | 4.0 M | from 1.8 GB |
| 76 | Qwen3-4B-Instruct-2507 | 4.0 B | 262 K | ✓ apache-2.0 | 4.0 M | from 10.0 GB |
| 77 | Qwen3.8-27B-iMatrix-NVFP4-MTP-GGUF | — | — | ✓ apache-2.0 | 4.0 M | from 19.3 GB |
| 78 | Qwen3-1.7B | 2.0 B | 41 K | ✓ apache-2.0 | 3.8 M | from 5.3 GB |
| 79 | Ornith-1.0-35B-GGUF | — | — | ✓ mit | 3.8 M | from 23.8 GB |
| 80 | wav2vec2-large-xlsr-53-polish | — | — | ✓ apache-2.0 | 3.7 M | — |
| 81 | Qwen3-VL-4B-Instruct | 4.4 B | — | ✓ apache-2.0 | 3.7 M | from 10.9 GB |
| 82 | distilbert-base-uncased-finetuned-sst-2-english | 70 M | 512 | ✓ apache-2.0 | 3.7 M | from 0.8 GB |
| 83 | Qwen3.6-27B | 27.8 B | — | ✓ apache-2.0 | 3.6 M | from 65.8 GB |
| 84 | Kimi-K3-DSpark | 2.3 B | 1.0 M | unknown | 3.6 M | from 5.8 GB |
| 85 | Qwen2.5-7B-Instruct-AWQ | 7.6 B | 33 K | ✓ apache-2.0 | 3.5 M | from 7.8 GB |
| 86 | NVIDIA-Nemotron-3-Nano-4B-BF16 | 4.0 B | 262 K | other | 3.5 M | from 9.8 GB |
| 87 | pythia-160m | 210 M | 2 K | ✓ apache-2.0 | 3.5 M | from 0.9 GB |
| 88 | bert-large-cased-finetuned-conll03-english | 330 M | 512 | unknown | 3.4 M | from 2.0 GB |
| 89 | nsfw_image_detection | 90 M | — | ✓ apache-2.0 | 3.4 M | from 0.9 GB |
| 90 | Qwen3.6-35B-A3B | 36.0 B | — | ✓ apache-2.0 | 3.3 M | from 85.0 GB |
| 91 | Ornith-1.0-9B-GGUF | — | — | ✓ mit | 3.3 M | from 6.7 GB |
| 92 | nomic-embed-text-v1 | 140 M | 8 K | ✓ apache-2.0 | 3.2 M | from 1.1 GB |
| 93 | twitter-roberta-base-sentiment-latest | — | 512 | ✓ cc-by-4.0 | 3.2 M | — |
| 94 | wav2vec2-large-xlsr-53-dutch | — | — | ✓ apache-2.0 | 3.1 M | — |
| 95 | wav2vec2-indonesian-javanese-sundanese | — | — | ✓ apache-2.0 | 3.1 M | — |
| 96 | Qwen3-VL-2B-Instruct | 2.1 B | — | ✓ apache-2.0 | 3.0 M | from 5.5 GB |
| 97 | Florence-2-base | 230 M | — | ✓ mit | 3.0 M | from 1.0 GB |
| 98 | stable-diffusion-xl-base-1.0 | 2.6 B | — | ⚠ openrail++ | 3.0 M | from 39.7 GB |
| 99 | all-MiniLM-L6-v2 | 20 M | 512 | ✓ apache-2.0 | 3.0 M | from 0.5 GB |
| 100 | gemma-3-1b-it | 1.0 B | — | ⚠ gemma | 2.9 M | from 2.8 GB |
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.