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 |
|---|---|---|---|---|---|---|
| 1001 | Meta-Llama-3.1-70B-Instruct-AWQ-INT4 | 70.6 B | 131 K | ⚠ llama3.1 | 140 K | from 54.8 GB |
| 1002 | xlnet-base-cased | — | — | ✓ mit | 140 K | — |
| 1003 | Qwen3-235B-A22B-Instruct-2507 | 235.1 B | 262 K | ✓ apache-2.0 | 139 K | from 553.0 GB |
| 1004 | Meta-Llama-3-8B | 8.0 B | — | ⚠ llama3 | 139 K | from 19.4 GB |
| 1005 | humanizer | 12.0 B | — | ✓ apache-2.0 | 139 K | from 6.6 GB |
| 1006 | typhoon2.5-qwen3-4b | 4.0 B | 262 K | ✓ apache-2.0 | 138 K | from 10.0 GB |
| 1007 | Qwen-Image-2.1-GGUF | — | — | unknown | 138 K | from 3.3 GB |
| 1008 | FLUX.1-schnell-gguf | — | — | ✓ apache-2.0 | 137 K | from 4.9 GB |
| 1009 | opus-mt-en-es | — | 512 | ✓ apache-2.0 | 135 K | — |
| 1010 | Wan2.2-I2V_General-NSFW-LoRA | — | — | unknown | 126 K | from 1.8 GB |
| 1011 | Ministral-3-14B-Instruct-2512 | 13.9 B | — | ✓ apache-2.0 | 125 K | from 37.2 GB |
| 1012 | opus-mt-ru-en | — | 512 | ✓ cc-by-4.0 | 122 K | — |
| 1013 | Z-Image-GGUF | 6.2 B | — | ✓ apache-2.0 | 120 K | from 5.8 GB |
| 1014 | waiIllustriousSDXL_v170 | — | — | cdla-permissive-2.0 | 117 K | from 8.1 GB |
| 1015 | lcm-lora-sdv1-5 | — | — | ⚠ openrail++ | 116 K | from 0.6 GB |
| 1016 | GLM-4.5 | 358.3 B | 131 K | ✓ mit | 114 K | from 842.6 GB |
| 1017 | janku-v5-nsfw-trained-noobai-rou-wei-illustrious-xl-v50-sdxl | 2.6 B | — | other | 112 K | from 8.5 GB |
| 1018 | Illustrious-xl-early-release-v0 | 2.6 B | — | other | 112 K | from 23.8 GB |
| 1019 | NetaYume-Lumina-Image-2.0 | — | — | ✓ apache-2.0 | 112 K | from 99.5 GB |
| 1020 | Chroma-GGUF | — | — | ✓ apache-2.0 | 111 K | from 6.0 GB |
| 1021 | opus-mt-it-en | — | 512 | ✓ apache-2.0 | 110 K | — |
| 1022 | amanatsu-illustrious-v11-sdxl | 2.6 B | — | other | 106 K | from 8.5 GB |
| 1023 | Krea2_FP8 | — | — | other | 105 K | from 20.7 GB |
| 1024 | opus-mt-tc-big-ko-en | 210 M | 1 K | ✓ cc-by-4.0 | 103 K | from 1.0 GB |
| 1025 | Flux2-Klein-9B-True-V2 | — | — | other | 102 K | from 6.8 GB |
| 1026 | Qwen-Image-GGUF | — | — | ✓ apache-2.0 | 100 K | from 8.4 GB |
| 1027 | Realistic_Vision_V6.0_B1_noVAE | — | — | ⚠ creativeml-openrail-m | 99 K | from 14.6 GB |
| 1028 | opus-mt-ar-en | — | 512 | ✓ apache-2.0 | 99 K | — |
| 1029 | Z-Image-Turbo-GGUF | — | — | ✓ apache-2.0 | 97 K | from 3.4 GB |
| 1030 | Qwen2.5-VL-72B-Instruct | 73.4 B | 128 K | other | 96 K | from 173.0 GB |
| 1031 | opus-mt-ko-en | — | 512 | ✓ apache-2.0 | 96 K | — |
| 1032 | Hy-MT2-30B-A3B | 30.1 B | 262 K | ✓ apache-2.0 | 95 K | from 71.2 GB |
| 1033 | ideogram-4-gguf | 9.3 B | — | other | 94 K | from 8.1 GB |
| 1034 | Qwen-Image-2512-Lightning | 20.4 B | — | ✓ apache-2.0 | 93 K | from 121.8 GB |
| 1035 | Ministral-3-3B-Instruct-2512 | 3.8 B | — | ✓ apache-2.0 | 92 K | from 11.4 GB |
| 1036 | Krea-2-Turbo-GGUF | — | — | other | 91 K | from 5.9 GB |
| 1037 | MiMo-V2.6-Flash-RL | 310.8 B | 1.0 M | ✓ mit | 91 K | from 242.6 GB |
| 1038 | Kimi-K2.7-Code | 1,026.9 B | — | other | 91 K | from 809.2 GB |
| 1039 | stable-diffusion-xl-1.0-inpainting-0.1 | 2.6 B | — | ⚠ openrail++ | 90 K | from 23.8 GB |
| 1040 | Z-Image-Lora | — | — | ✓ apache-2.0 | 90 K | from 108.1 GB |
| 1041 | envit5-translation | — | — | ⚠ openrail | 89 K | — |
| 1042 | Ministral-3-8B-Instruct-2512 | 8.9 B | — | ✓ apache-2.0 | 86 K | from 24.8 GB |
| 1043 | Krea-2-Raw | 12.8 B | — | other | 85 K | from 70.6 GB |
| 1044 | CyberRealisticPony | — | — | ⚠ creativeml-openrail-m | 84 K | from 298.0 GB |
| 1045 | T5-base-10K-summarization | 220 M | — | unknown | 84 K | from 1.5 GB |
| 1046 | Hy3-preview | 298.8 B | 262 K | other | 82 K | from 702.7 GB |
| 1047 | granite-4.2-8b | 8.8 B | 131 K | ✓ apache-2.0 | 80 K | from 21.2 GB |
| 1048 | GLM-4.7 | 358.3 B | 203 K | ✓ mit | 80 K | from 842.6 GB |
| 1049 | nunchaku-qwen-image-edit | — | — | ✓ apache-2.0 | 80 K | from 162.9 GB |
| 1050 | Krea-2-Turbo | 12.8 B | — | other | 80 K | from 70.6 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.