1,023 models · refreshed nightly

Models that run on RTX 4090 · 24 GB

Every model in the catalog with its licence, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

All text-generation 400 text-to-image 151 ASR 89 image-text-to-text 84 sentence-similarity 57 feature-extraction 48 translation 47 text-classification 39 image-classification 33 token-classification 23 text-to-speech 17 audio-classification 12 image-segmentation 8 object-detection 8 summarization 7

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

657 models

#	Model	Params	Context	Commercial use	30d	On RTX 4090 · 24 GB
651	epiCRealism emilianJR · text-to-image	860 M	—	⚠ creativeml-openrail-m	16 K	6.7 GB
652	FLUX.1-dev-ControlNet-Union-Pro-2.0 Shakker-Labs · text-to-image	2.1 B	—	other	16 K	5.5 GB
653	stable-diffusion-3.5-medium-GGUF second-state · text-to-image	—	—	other	16 K	2.0 GB
654	controlnet-tile-sdxl-1.0 xinsir · text-to-image	1.3 B	—	✓ apache-2.0	16 K	3.4 GB
655	controlnet-depth-sdxl-1.0 xinsir · text-to-image	1.3 B	—	✓ apache-2.0	16 K	3.4 GB
656	ProteusV0.3 dataautogpt3 · text-to-image	—	—	gpl-3.0	16 K	8.1 GB
657	ProteusV0.2 dataautogpt3 · text-to-image	—	—	gpl-3.0	16 K	8.1 GB

VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.