AImodelsComparison.com 1,000 models
Menu
Models Best of Trending Can I run it? Methodology About
1,000 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.

Task
All text-generation 400 text-to-image 150 ASR 88 image-text-to-text 80 sentence-similarity 55 feature-extraction 45 translation 43 text-classification 39 image-classification 32 token-classification 21 text-to-speech 12 audio-classification 10 object-detection 10 image-segmentation 8 summarization 7
Runs on
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
Licence
Size
$
680 models
#ModelParamsContextCommercial use30dOn RTX 4090 · 24 GB
651 Krea2-realism-V2 RudySen · text-to-image — — ✓ mit 34 K 2.2 GB
652 z-image-turbo-nsfw-v2-GGUF lesliemore · text-to-image — — ✓ apache-2.0 33 K 8.4 GB
653 autismmix-sdxl-autismmix-pony-sdxl John6666 · text-to-image 2.6 B — other 32 K 8.5 GB
654 stable-diffusion-2-1-base Manojb · text-to-image 870 M — ⚠ openrail++ 32 K 20.6 GB
655 FLUX.2-klein-9B-GGUF leejet · text-to-image — — unknown 32 K 6.7 GB
656 Krea2-Turbo-Distill-4step-LoRA lvladikov · text-to-image — — other 32 K 11.1 GB
657 Real-Qwen-Image-V2 wikeeyang · text-to-image — — ✓ apache-2.0 31 K 14.9 GB
658 ideogram-4-nf4 ideogram-ai · text-to-image · gated 4.8 B — other 31 K 18.9 GB
659 stable-diffusion-v1-5-GGUF second-state · text-to-image — — ⚠ creativeml-openrail-m 31 K 2.2 GB
660 controlnet-depth-sdxl-1.0 diffusers · text-to-image 1.3 B — ⚠ openrail++ 31 K 8.9 GB
661 mv-adapter huanngzh · text-to-image — — ✓ apache-2.0 30 K 23.4 GB
662 minecraft-skin-generator-sdxl monadical-labs · text-to-image 2.6 B — ⚠ openrail 30 K 14.2 GB
663 FLUX.1-dev-GGUF unsloth · text-to-image — — other 30 K 4.9 GB
664 FLUX.2-klein-4B-GGUF leejet · text-to-image — — ✓ apache-2.0 29 K 3.2 GB
665 flux2-klein-9b-uncensored-text-encoder-Q8_0-GGUF WANG-CC · text-to-image — — other 29 K 10.1 GB
666 Krea2-Turbo-HD-V1 wikeeyang · text-to-image — — other 29 K 9.5 GB
667 controlnet-canny-sdxl-1.0 xinsir · text-to-image 1.3 B — ✓ apache-2.0 29 K 6.2 GB
668 pony-diffusion-v6-xl-GGUF offgrid-ai · text-to-image — — ⚠ creativeml-openrail-m 28 K 3.6 GB
669 nunchaku-flux.1-schnell nunchaku-ai · text-to-image — — ✓ apache-2.0 28 K 15.6 GB
670 mlx-FLUX.1-schnell-4bit-quantized argmaxinc · text-to-image — — ✓ apache-2.0 28 K 8.2 GB
671 pony-v7-base purplesmartai · text-to-image 6.9 B — other 28 K 5.9 GB
672 SenseNova-U1.5-8B_GGUFs realrebelai · text-to-image 8.0 B — ✓ apache-2.0 27 K 11.9 GB
673 LLaDa-Image-Turbo_ComfyUI realrebelai · text-to-image — — unknown 27 K 10.6 GB
674 Flux_Lustly.ai_Uncensored_nsfw_v1 lustlyai · text-to-image — — ⚠ creativeml-openrail-m 26 K 0.9 GB
675 DaSiWa_MiniMax_H3 lynaNSFW · text-to-image — — unknown 26 K 23.6 GB
676 noobai-XL-1.0 Laxhar · text-to-image 2.6 B — other 26 K 16.1 GB
677 controlnet-canny-sdxl-1.0 diffusers · text-to-image 1.3 B — ⚠ openrail++ 26 K 8.9 GB
678 bigaspv2-5 fancyfeast · text-to-image 2.6 B — unknown 26 K 16.1 GB
679 picx-real GraydientPlatformAPI · text-to-image 860 M — ⚠ openrail 25 K 3.6 GB
680 flux-klein-9b-Biglove-Collection AgentAnon · text-to-image — — ✗ cc-by-nc-4.0 24 K 7.6 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.