1,222 models · 1,222 open weights · 200 API-only · refreshed nightly
Open-weights models
Models whose weights are published on Hugging Face — download them and run them on your own hardware. Many are also served by hosted providers; those carry an "Also via API" badge with live prices.
| # | Model | Params | Context | Commercial use | 30d | Min VRAM |
|---|---|---|---|---|---|---|
| 851 | Nemotron-Labs-Diffusion-8B | 8.5 B | 262 K | other | 204 K | from 20.6 GB |
| 852 | granite-guardian-3.3-8b | 8.2 B | 131 K | ✓ apache-2.0 | 204 K | from 19.7 GB |
| 853 | Llama-3_3-Nemotron-Super-49B-v1_5-FP8 | 49.9 B | 131 K | other | 204 K | from 65.1 GB |
| 854 | Ornith-1.5-9B-MLX-6bit | 9.0 B | — | unknown | 204 K | from 9.8 GB |
| 855 | ftrobertallm | 355 M | 512 | ✓ mit | 204 K | from 2.1 GB |
| 856 | DeepSeek-V2-Lite-Chat | 15.7 B | 164 K | other | 204 K | from 37.4 GB |
| 857 | MiniMax-M3 | 427.0 B | — | other | 203 K | from 1,004.2 GB |
| 858 | Llama-3.1-70B-Instruct | 70.6 B | — | ⚠ llama3.1 | 203 K | from 166.3 GB |
| 859 | Qwen3-30B-A3B-abliterated | 30.5 B | 41 K | ✓ apache-2.0 | 203 K | from 206.6 GB |
| 860 | gemma-4-31B-it-uncensored | 32.7 B | — | ✓ apache-2.0 | 203 K | from 74.2 GB |
| 861 | DeepSeek-V4-Flash-NVFP4 | 166.7 B | 1.0 M | ✓ mit | 203 K | from 210.6 GB |
| 862 | GLM-5-FP8 | 753.9 B | 203 K | ✓ mit | 203 K | from 945.4 GB |
| 863 | prompt-saturation-attack-detector | 4.4 M | 512 | unknown | 203 K | from 0.5 GB |
| 864 | DeepSeek-V4-Flash-0731-NVFP4 | 304.2 B | 1.0 M | ✓ mit | 203 K | from 239.2 GB |
| 865 | medgemma-27b-text-it-GPTQ | 4.8 B | 131 K | other | 202 K | from 18.8 GB |
| 866 | yolov8m-table-extraction | 8.0 M | — | agpl-3.0 | 202 K | from 0.5 GB |
| 867 | Qwen2.5-7B-Instruct-GGUF | — | — | ✓ apache-2.0 | 202 K | from 3.6 GB |
| 868 | LFM2.5-1.2B-Instruct | 1.2 B | 128 K | other | 201 K | from 3.3 GB |
| 869 | Yi-Coder-9B-Chat-GGUF | — | — | unknown | 201 K | from 2.7 GB |
| 870 | Dolphin-Mistral-24B-Venice-Edition | 24.0 B | — | ✓ apache-2.0 | 201 K | from 56.9 GB |
| 871 | xlm-roberta-base-language-detection | 280 M | 512 | ✓ mit | 201 K | from 1.8 GB |
| 872 | OpenMed-NER-DiseaseDetect-BioMed-335M | 334 M | 512 | ✓ apache-2.0 | 201 K | from 1.3 GB |
| 873 | stable-diffusion-inpainting | — | — | ⚠ creativeml-openrail-m | 201 K | from 3.5 GB |
| 874 | OLMoE-1B-7B-0125-Instruct | 6.9 B | 4 K | ✓ apache-2.0 | 201 K | from 16.8 GB |
| 875 | Qwen_Qwen3-Next-80B-A3B-Thinking-GGUF | — | — | ✓ apache-2.0 | 200 K | from 18.7 GB |
| 876 | GLM-5.1-FP8 | 753.9 B | 203 K | ✓ mit | 200 K | from 945.4 GB |
| 877 | Qwen3.5-35B-A3B-APEX-GGUF | — | — | ✓ apache-2.0 | 200 K | from 28.4 GB |
| 878 | glm-4-9b-chat-IMat-GGUF | — | — | other | 200 K | from 3.9 GB |
| 879 | VLM2Vec-Full | 4.2 B | 131 K | ✓ apache-2.0 | 199 K | from 10.2 GB |
| 880 | c4ai-command-r-v01 | 35.0 B | — | ✗ cc-by-nc-4.0 | 199 K | from 82.7 GB |
| 881 | GLM-4.7-Flash | 31.2 B | 203 K | ✓ mit | 199 K | from 73.9 GB |
| 882 | Qwen2.5-7B-Instruct-1M | 7.6 B | 1.0 M | ✓ apache-2.0 | 197 K | from 18.4 GB |
| 883 | t5-large | 740 M | — | ✓ apache-2.0 | 197 K | from 3.9 GB |
| 884 | gemma-4-12b-heretic-abliterated-GGUF | — | — | ✓ apache-2.0 | 196 K | from 0.7 GB |
| 885 | Laguna-S-2.1-GGUF | — | — | openmdw-1.1 | 196 K | from 37.6 GB |
| 886 | Qwen2.5-Coder-32B-Instruct-GGUF | — | — | ✓ apache-2.0 | 196 K | from 9.1 GB |
| 887 | Qwen3.6-27B-Text-NVFP4-MTP | 16.7 B | — | ✓ apache-2.0 | 196 K | from 24.6 GB |
| 888 | Kimi-K2.7-Code-NVFP4 | — | — | other | 196 K | from 655.2 GB |
| 889 | llama-3-8b-instruct-awq | 8.0 B | 8 K | unknown | 196 K | from 8.0 GB |
| 890 | GLM-5.2-AWQ-INT4 | 753.3 B | 1.0 M | ✓ mit | 196 K | from 635.1 GB |
| 891 | Laguna-XS-2.1-GGUF | — | — | openmdw-1.1 | 196 K | from 22.8 GB |
| 892 | Qwen2.5-3B | 3.1 B | 33 K | other | 196 K | from 7.8 GB |
| 893 | TinyStories-1M | 1.0 M | 2 K | unknown | 195 K | from 0.5 GB |
| 894 | SmolLM2-360M-Instruct | 360 M | 8 K | ✓ apache-2.0 | 195 K | from 1.4 GB |
| 895 | Fanar-1-9B-Instruct | 8.8 B | 4 K | ✓ apache-2.0 | 195 K | from 21.1 GB |
| 896 | Qwen2.5-3B-Instruct-unsloth-bnb-4bit | 3.2 B | 33 K | ✓ apache-2.0 | 195 K | from 3.6 GB |
| 897 | Huihui-Qwen3.6-27B-abliterated-NVFP4-MTP | 27.0 B | — | ✓ apache-2.0 | 195 K | from 27.2 GB |
| 898 | Qwen2.5-1.5B-Instruct-AWQ | 1.8 B | 33 K | ✓ apache-2.0 | 195 K | from 2.5 GB |
| 899 | Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUF | 27.0 B | — | ✓ apache-2.0 | 195 K | from 5.2 GB |
| 900 | Llama-Guard-3-8B | 8.0 B | — | ⚠ llama3.1 | 195 K | from 19.4 GB |
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.