1,086 models · 1,086 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.

All 1,286 Open weights (self-host) 1,086 API-only 200

All text-generation 461 text-to-image 150 image-text-to-text 101 ASR 83 sentence-similarity 56 translation 46 feature-extraction 44 text-classification 43 image-classification 36 token-classification 17 text-to-speech 17 audio-classification 9 image-segmentation 8 object-detection 7 summarization 6 audio-text-to-text 1 any-to-any 1

Any RTX 3060 · 12 GB RTX 4070 · 16 GB RTX 4090 · 24 GB 2 × 24 GB Mac M3 · 24 GB Mac M4 Max · 64 GB

461 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
451	Nex-N2.5-Pro nex-agi · text-generation Open weights Also via API	396.8 B	—	✓ apache-2.0	2 K	from 507.9 GB
452	UnslopNemo-12B-v4.1 TheDrummer · text-generation Open weights Also via API	12.2 B	1.0 M	unknown	2 K	from 29.3 GB
453	L3-8B-Lunaris-v1 Sao10K · text-generation Open weights Also via API	8.0 B	8 K	⚠ llama3	2 K	from 19.4 GB
454	c4ai-command-a-03-2025 CohereLabs · text-generation · gated Open weights Also via API	111.1 B	—	✗ cc-by-nc-4.0	1 K	from 261.5 GB
455	Hermes-3-Llama-3.1-405B NousResearch · text-generation Open weights Also via API	405.9 B	131 K	⚠ llama3	1 K	from 954.3 GB
456	MythoMax-L2-13b Gryphe · text-generation Open weights Also via API	13.0 B	4 K	other	1 K	from 31.1 GB
457	Hermes-4-405B NousResearch · text-generation Open weights Also via API	405.9 B	131 K	⚠ llama3	1 K	from 954.3 GB
458	reka-flash-3 RekaAI · text-generation Open weights Also via API	20.9 B	33 K	✓ apache-2.0	901	from 49.6 GB
459	magnum-v4-72b anthracite-org · text-generation Open weights Also via API	72.7 B	33 K	✓ apache-2.0	880	from 171.4 GB
460	ReMM-SLERP-L2-13B Undi95 · text-generation Open weights Also via API	13.0 B	4 K	✗ cc-by-nc-4.0	729	from 31.1 GB
461	L3.1-70B-Euryale-v2.2 Sao10K · text-generation Open weights Also via API	70.0 B	131 K	✗ cc-by-nc-4.0	544	from 165.0 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.