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 |
|---|---|---|---|---|---|---|
| 901 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark | 760 M | 1.0 M | other | 195 K | from 2.1 GB |
| 902 | TinyLlama-1.1B-Chat-v0.3-GPTQ | 1.1 B | 2 K | ✓ apache-2.0 | 195 K | from 1.5 GB |
| 903 | Qwen3.6-35B-A3B-Claude-4.6-Opus-Reasoning-Distilled-GGUF | — | — | ✓ apache-2.0 | 194 K | from 23.8 GB |
| 904 | GLM-5.2-NVFP4 | 381.0 B | 1.0 M | ✓ mit | 194 K | from 569.0 GB |
| 905 | Common-Voice-Gender-Detection | 95 M | — | ✓ apache-2.0 | 194 K | from 1.3 GB |
| 906 | supergemma4-26b-uncensored-gguf-v2 | — | — | ⚠ gemma | 194 K | from 19.0 GB |
| 907 | QwQ-32B | 32.8 B | 41 K | ✓ apache-2.0 | 194 K | from 77.5 GB |
| 908 | rtdetr_r50vd | 40 M | — | ✓ apache-2.0 | 194 K | from 0.7 GB |
| 909 | Qwen2.5-Coder-7B-Instruct | 7.6 B | 33 K | ✓ apache-2.0 | 193 K | from 18.4 GB |
| 910 | regnety_032.ra_in1k | 20 M | — | ✓ apache-2.0 | 193 K | from 0.6 GB |
| 911 | MiniCPM5-2B-GGUF | 2.0 B | — | ✓ apache-2.0 | 192 K | from 2.5 GB |
| 912 | Meta-Llama-3-8B-Instruct-abliterated-v3 | 8.0 B | 8 K | ⚠ llama3 | 192 K | from 19.4 GB |
| 913 | animagine-xl-3.1 | 2.6 B | — | ⚠ openrail++ | 191 K | from 16.1 GB |
| 914 | accent-id-commonaccent_ecapa | — | — | ✓ mit | 191 K | — |
| 915 | falcon-7b | 7.2 B | — | ✓ apache-2.0 | 190 K | from 17.5 GB |
| 916 | Meta-Llama-3.1-8B-Instruct | 8.0 B | 131 K | ⚠ llama3.1 | 189 K | from 19.4 GB |
| 917 | NVIDIA-Nemotron-3.5-Lightning-30B-A3B-GGUF | 30.0 B | 262 K | other | 189 K | from 25.8 GB |
| 918 | Qwen3-30B-A3B-Instruct-2507-AWQ-4bit | 30.0 B | 262 K | ✓ apache-2.0 | 188 K | from 24.9 GB |
| 919 | Krea-2-Turbo | 12.8 B | — | other | 188 K | from 70.6 GB |
| 920 | revanimated | — | — | ⚠ creativeml-openrail-m | 188 K | — |
| 921 | Qwen2.5-7B-Instruct-GGUF | 7.0 B | 33 K | ✓ apache-2.0 | 187 K | from 4.9 GB |
| 922 | EuroLLM-1.7B-Instruct | 1.7 B | 4 K | ✓ apache-2.0 | 187 K | from 4.4 GB |
| 923 | DeepSeek-R1-0528-Qwen3-8B-MLX-4bit | 1.3 B | 131 K | ✓ mit | 186 K | from 5.8 GB |
| 924 | Mistral-Small-3.2-24B-Instruct-2506 | 24.0 B | — | ✓ apache-2.0 | 186 K | from 109.8 GB |
| 925 | opt-350m | 350 M | 2 K | other | 185 K | from 1.3 GB |
| 926 | Qwen1.5-1.8B-Chat | 1.8 B | 33 K | other | 185 K | from 4.8 GB |
| 927 | Laguna-S-2.1-APEX-GGUF | 117.6 B | 1.0 M | openmdw-1.1 | 185 K | from 18.9 GB |
| 928 | Agents-A1-4B-Q4_K_M-GGUF | 4.0 B | — | ✓ apache-2.0 | 185 K | from 1.8 GB |
| 929 | OTel-2.0-LLM-31B-IT-QLoRA | 31.3 B | — | ✓ apache-2.0 | 184 K | from 74.0 GB |
| 930 | Qwen2-7B-Instruct | 7.6 B | 33 K | ✓ apache-2.0 | 183 K | from 18.4 GB |
| 931 | Mistral-Nemo-Instruct-2407 | 12.2 B | 131 K | ✓ apache-2.0 | 183 K | from 56.2 GB |
| 932 | Ornith-1.5-35B-A3B-MLX-8bit | 34.7 B | — | unknown | 181 K | from 46.2 GB |
| 933 | opus-mt-en-fr | — | 512 | ✓ apache-2.0 | 181 K | — |
| 934 | Qwen-Image-2.1-Turbo-GGUF | — | — | other | 180 K | from 3.3 GB |
| 935 | Qwen-Image-2.1 | 7.1 B | — | other | 180 K | from 38.0 GB |
| 936 | h2o-danube3-500m-chat | 514 M | 8 K | ✓ apache-2.0 | 179 K | from 1.7 GB |
| 937 | Llama-2-13b-chat-hf | 13.0 B | — | ⚠ llama2 | 178 K | from 31.1 GB |
| 938 | Ornith-1.0-397B | 396.8 B | — | ✓ mit | 177 K | from 933.0 GB |
| 939 | llama-7b | 6.7 B | 2 K | other | 177 K | from 16.3 GB |
| 940 | LFM2.5-24B-A2B-GGUF | 24.0 B | 131 K | other | 177 K | from 19.0 GB |
| 941 | Llama-3.1-8B-Instruct | 8.0 B | 131 K | ⚠ llama3.1 | 177 K | from 19.4 GB |
| 942 | HunyuanDiT-v1.1-Diffusers-Distilled | 1.5 B | — | other | 176 K | from 16.7 GB |
| 943 | DialoGPT-medium | — | — | ✓ mit | 174 K | — |
| 944 | Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16 | 33.0 B | — | other | 174 K | from 78.1 GB |
| 945 | Ornith-1.5-35B-A3B-MLX-4bit | 34.7 B | — | unknown | 173 K | from 27.2 GB |
| 946 | Qwen3-1.7B-GGUF | 1.7 B | 41 K | ✓ apache-2.0 | 173 K | from 2.8 GB |
| 947 | Qwen2.5-Coder-14B-Instruct-GGUF | 14.0 B | 33 K | ✓ apache-2.0 | 172 K | from 8.9 GB |
| 948 | deepseek-v4-flash-0731-spark | 60.3 B | 1.0 M | ✓ mit | 171 K | from 127.0 GB |
| 949 | GLM-5.2-GGUF | — | — | ✓ mit | 170 K | from 52.0 GB |
| 950 | GLM-4.7-Flash-MLX-8bit | 29.9 B | 203 K | ✓ mit | 170 K | from 40.0 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.