1,060 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 |
|---|---|---|---|---|---|---|
| 701 | Meta-Llama-3.1-8B-Instruct | 8.0 B | 131 K | ⚠ llama3.1 | 307 K | from 19.4 GB |
| 702 | HunyuanDiT-v1.1-Diffusers-Distilled | 1.5 B | — | other | 306 K | from 16.7 GB |
| 703 | Dolphin-Mistral-24B-Venice-Edition | 24.0 B | — | ✓ apache-2.0 | 306 K | from 56.9 GB |
| 704 | llmlingua-2-bert-base-multilingual-cased-meetingbank | 180 M | 512 | ✓ apache-2.0 | 306 K | from 1.3 GB |
| 705 | Qwen3-Next-80B-A3B-Instruct | 81.3 B | 262 K | ✓ apache-2.0 | 306 K | from 191.6 GB |
| 706 | Qwen-Image | 20.4 B | — | ✓ apache-2.0 | 306 K | from 67.0 GB |
| 707 | gpt2-medium | 380 M | — | ✓ mit | 305 K | from 2.2 GB |
| 708 | Qwen2.5-Coder-7B-Instruct-GGUF | — | — | ✓ apache-2.0 | 305 K | from 3.8 GB |
| 709 | sarvam-30b | 32.2 B | 131 K | ✓ apache-2.0 | 304 K | from 146.8 GB |
| 710 | prokbert-mini-promoter | 20 M | 1 K | ✗ cc-by-nc-4.0 | 302 K | from 0.6 GB |
| 711 | SmolLM2-360M-Instruct | 360 M | 8 K | ✓ apache-2.0 | 302 K | from 1.4 GB |
| 712 | Qwen2-0.5B-Instruct | 490 M | 33 K | ✓ apache-2.0 | 300 K | from 1.7 GB |
| 713 | Qwen2.5-14B-bnb-4bit | 15.2 B | 131 K | ✓ apache-2.0 | 297 K | from 13.7 GB |
| 714 | opt-350m | 350 M | 2 K | other | 294 K | from 1.3 GB |
| 715 | Qwen2.5-7B-Instruct | 7.6 B | 33 K | ✓ apache-2.0 | 294 K | from 18.4 GB |
| 716 | Llama-3.2-3B-Instruct-FP8-dynamic | 3.6 B | 131 K | ⚠ llama3.2 | 294 K | from 5.9 GB |
| 717 | DeepSeek-R1-0528-Qwen3-8B-MLX-4bit | 1.3 B | 131 K | ✓ mit | 293 K | from 5.8 GB |
| 718 | The_GuageLLM_23M | 20 M | — | ✓ apache-2.0 | 292 K | from 0.6 GB |
| 719 | nllb-200-distilled-1.3B | 1.3 B | 1 K | ✗ cc-by-nc-4.0 | 292 K | from 3.6 GB |
| 720 | voice-gender-classifier | 20 M | — | ✓ mit | 291 K | from 0.6 GB |
| 721 | supergemma4-26b-uncensored-gguf-v2 | — | — | ⚠ gemma | 289 K | from 19.0 GB |
| 722 | Qwen3-0.6B-GGUF | — | — | unknown | 288 K | from 0.9 GB |
| 723 | mask2former-swin-large-ade-semantic | 220 M | — | other | 287 K | from 1.5 GB |
| 724 | MiMo-V2.5 | 310.8 B | 1.0 M | ✓ mit | 287 K | from 394.4 GB |
| 725 | Jan-v3.5-4B-gguf | — | — | ✓ apache-2.0 | 286 K | from 2.8 GB |
| 726 | Qwen3.5-4B-Claude-4.6-Opus-Reasoning-Distilled-GGUF | — | — | ✓ apache-2.0 | 286 K | from 2.5 GB |
| 727 | Qwopus-GLM-18B-Merged-GGUF | — | — | ✓ apache-2.0 | 286 K | from 9.2 GB |
| 728 | vit_base_patch8_224.augreg2_in21k_ft_in1k | 90 M | — | ✓ apache-2.0 | 285 K | from 0.9 GB |
| 729 | DeepSeek-V3.1 | 684.5 B | 164 K | ✓ mit | 285 K | from 860.6 GB |
| 730 | Apodex-1.1-mini-GGUF | — | — | ✓ apache-2.0 | 283 K | from 10.2 GB |
| 731 | mamba-130m-hf | 130 M | — | unknown | 282 K | from 1.1 GB |
| 732 | Llama-3.2-1B-Instruct-FP8-dynamic | 1.5 B | 131 K | ⚠ llama3.2 | 282 K | from 3.0 GB |
| 733 | vit-age-classifier | 90 M | — | unknown | 279 K | from 0.9 GB |
| 734 | Llama-Guard-3-1B | 1.5 B | 131 K | ⚠ llama3.2 | 277 K | from 4.0 GB |
| 735 | Qwen2.5-3B-Instruct-GGUF | — | — | other | 277 K | from 2.0 GB |
| 736 | gemma-4-31B-it-scotoma-2-GGUF | — | — | ✓ apache-2.0 | 277 K | from 13.8 GB |
| 737 | deepseek-coder-6.7b-instruct | 6.7 B | 16 K | other | 277 K | from 16.3 GB |
| 738 | MiniMax-M2 | 228.7 B | 197 K | other | 277 K | from 288.0 GB |
| 739 | Ornith-1.5-9B-MLX-4bit | 9.0 B | — | unknown | 276 K | from 7.4 GB |
| 740 | Spark-X2.5-4B-GGUF | 4.0 B | — | ✓ apache-2.0 | 275 K | from 4.0 GB |
| 741 | vit_tiny_r_s16_p8_224.augreg_in21k | 10 M | — | ✓ apache-2.0 | 274 K | from 0.5 GB |
| 742 | koelectra-polite-v1 | — | 512 | unknown | 272 K | — |
| 743 | Qwen3-0.6B-FP8 | 750 M | 41 K | ✓ apache-2.0 | 271 K | from 1.8 GB |
| 744 | segformer-b2-finetuned-ade-512-512 | — | — | other | 271 K | — |
| 745 | DeepSeek-R1-0528-Qwen3-8B-MLX-8bit | 2.3 B | 131 K | ✓ mit | 270 K | from 10.4 GB |
| 746 | tiny_starcoder_py | 160 M | — | bigcode-openrail-m | 270 K | from 1.2 GB |
| 747 | EuroLLM-22B-Instruct-2512 | 22.6 B | 33 K | ✓ apache-2.0 | 270 K | from 53.7 GB |
| 748 | CodonTransformer | 90 M | 4 K | ✓ apache-2.0 | 270 K | from 0.9 GB |
| 749 | FLUX.1-dev-gguf | — | — | other | 270 K | from 4.9 GB |
| 750 | DeepSeek-V2-Lite | 15.7 B | 164 K | other | 270 K | from 37.4 GB |
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.