1,423 models · 1,213 open weights · 210 API-only · refreshed nightly

Models that run on RTX 4070 · 16 GB

Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

All 1,423 Open weights (self-host) 1,213 API-only 210

All text-generation 735 text-to-image 165 image-text-to-text 110 ASR 82 sentence-similarity 63 text-classification 50 translation 50 feature-extraction 46 image-classification 41 text-to-speech 23 token-classification 22 summarization 9 audio-classification 9 image-segmentation 9 object-detection 7 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

654 models

#	Model	Params	Context	Commercial use	30d	On RTX 4070 · 16 GB
651	wmt19-de-en facebook · translation Open weights	272 M	1 K	✓ apache-2.0	32 K	1.7 GB
652	HY-MT1.5-7B-GGUF tencent · translation Open weights	7.0 B	—	unknown	30 K	6.6 GB
653	Hy-MT2-1.8B tencent · translation Open weights Also via API	2.0 B	262 K	✓ apache-2.0	26 K	5.3 GB
654	moondream3.1-9B-A2B moondream · image-text-to-text Open weights Also via API	9.3 B	—	other	10 K	13.4 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.