1,089 models · 1,089 open weights · 210 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 | On 2 × 24 GB |
|---|---|---|---|---|---|---|
| 751 | indictrans2-en-indic-1B | 1.1 B | — | ✓ mit | 48 K | 5.6 GB |
| 752 | Hunyuan-MT-7B-GGUF | — | — | unknown | 47 K | 3.1 GB |
| 753 | Nemotron-3.5-Content-Safety | 4.3 B | — | other | 45 K | 10.6 GB |
| 754 | moondream3-preview | 9.3 B | — | other | 43 K | 42.7 GB |
| 755 | Hy-MT2-7B | 8.0 B | 262 K | ✓ apache-2.0 | 34 K | 19.4 GB |
| 756 | Hy-MT2-1.8B | 2.0 B | 262 K | ✓ apache-2.0 | 26 K | 5.3 GB |
| 757 | gpt-oss-safeguard-20b | 21.5 B | 131 K | ✓ apache-2.0 | 22 K | 18.9 GB |
| 758 | Ling-3.0-tiny | 7.9 B | 131 K | ✓ mit | 14 K | 19.1 GB |
| 759 | moondream3.1-9B-A2B | 9.3 B | — | other | 10 K | 13.4 GB |
| 760 | L3-8B-Lunaris-v1 | 8.0 B | 8 K | ⚠ llama3 | 2 K | 19.4 GB |
| 761 | UnslopNemo-12B-v4.1 | 12.2 B | 1.0 M | unknown | 2 K | 29.3 GB |
| 762 | MythoMax-L2-13b | 13.0 B | 4 K | other | 2 K | 31.1 GB |
| 763 | reka-edge-2603 | 7.1 B | — | other | 1 K | 17.3 GB |
| 764 | ReMM-SLERP-L2-13B | 13.0 B | 4 K | ✗ cc-by-nc-4.0 | 1 K | 31.1 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.