1,299 models · 1,213 open weights · 210 API-only · refreshed nightly

Models that run on 2 × 24 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 657 text-to-image 160 image-text-to-text 104 ASR 81 sentence-similarity 59 translation 44 text-classification 43 feature-extraction 41 image-classification 37 text-to-speech 23 token-classification 17 image-segmentation 9 summarization 8 audio-classification 8 object-detection 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

764 models

#	Model	Params	Context	Commercial use	30d	On 2 × 24 GB
No models match these filters.

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.