1,226 models · 1,226 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 1,426 Open weights (self-host) 1,226 API-only 200

All text-generation 534 text-to-image 155 image-text-to-text 112 ASR 86 sentence-similarity 64 translation 56 text-classification 51 feature-extraction 48 image-classification 39 token-classification 21 text-to-speech 19 audio-classification 12 image-segmentation 11 summarization 8 object-detection 8 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

112 models

#	Model	Params	Context	Commercial use	30d	Min VRAM
101	DeepSeek-V4.1-Flash-1017 deepseek-ai · image-text-to-text Open weights Also via API	763.2 B	—	✓ mit	58 K	from 676.3 GB
102	Llama-Guard-4-12B meta-llama · image-text-to-text · gated Open weights Also via API	12.0 B	—	other	44 K	from 28.7 GB
103	GLM-4.5V zai-org · image-text-to-text Open weights Also via API	107.7 B	—	✓ mit	26 K	from 253.6 GB
104	Step-3.7-Flash stepfun-ai · image-text-to-text Open weights Also via API	201.4 B	—	✓ apache-2.0	17 K	from 473.7 GB
105	Qwen3-VL-30B-A3B-Thinking Qwen · image-text-to-text Open weights Also via API	31.1 B	—	✓ apache-2.0	16 K	from 73.5 GB
106	Ling-3.0-flash-VL inclusionAI · image-text-to-text Open weights Also via API	124.8 B	—	✓ mit	13 K	from 293.9 GB
107	moondream3.1-9B-A2B moondream · image-text-to-text Open weights Also via API	9.3 B	—	other	10 K	from 13.4 GB
108	Llama-4-Maverick-17B-128E-Instruct meta-llama · image-text-to-text · gated Open weights Also via API	401.6 B	—	other	9 K	from 944.2 GB
109	Muse-Spark-Open-816B-A42B meta-models · image-text-to-text · gated Open weights Also via API	822.0 B	—	other	5 K	from 1,932.6 GB
110	GLM-4.6V zai-org · image-text-to-text Open weights Also via API	107.7 B	—	✓ mit	4 K	from 253.6 GB
111	MiniMax-M3.1-Flash MiniMaxAI · image-text-to-text Open weights Also via API	220.5 B	—	other	1 K	from 311.2 GB
112	reka-edge-2603 RekaAI · image-text-to-text Open weights Also via API	7.1 B	—	other	845	from 17.3 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.