AImodelsComparison.com 1,023 models
Menu
Models Best of Trending Can I run it? Methodology About
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.

Task
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
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
$
657 models
#ModelParamsContextCommercial use30dOn RTX 4090 · 24 GB
551 Gemma-4-26B-A4B-it-NVFP4 bg-digitalservices · text-generation 15.1 B — ✓ apache-2.0 168 K 20.8 GB
552 Meta-Llama-3.1-8B-Instruct-AWQ-INT4 hugging-quants · text-generation 8.0 B 131 K ⚠ llama3.1 167 K 8.0 GB
553 Qwen3-30B-A3B-GPTQ-Int4 Qwen · text-generation 30.5 B 41 K ✓ apache-2.0 167 K 23.7 GB
554 Agents-A1-4B InternScience · text-generation 4.5 B — ✓ apache-2.0 167 K 11.2 GB
555 Qwen2.5-Math-1.5B-Instruct Qwen · text-generation 1.5 B 4 K ✓ apache-2.0 167 K 4.1 GB
556 RnJ-1-Instruct-FP8 Doradus-AI · text-generation 8.8 B 33 K ⚠ gemma 164 K 15.0 GB
557 Llama-3.2-1B-Instruct-GGUF bartowski · text-generation — — ⚠ llama3.2 162 K 1.2 GB
558 Qwen3-4B-Instruct-2507-NVFP4 llmat · text-generation 2.8 B 262 K ✓ apache-2.0 161 K 4.9 GB
559 stable-diffusion-xl-1.0-inpainting-0.1 diffusers · text-to-image 2.6 B — ⚠ openrail++ 155 K 23.8 GB
560 opus-mt-tc-big-tr-en Helsinki-NLP · translation 230 M 1 K ✓ cc-by-4.0 154 K 1.1 GB
561 animagine-xl-3.1 cagliostrolab · text-to-image 2.6 B — ⚠ openrail++ 153 K 16.1 GB
562 nova-furry-xl-il-v120-sdxl John6666 · text-to-image 2.6 B — other 151 K 8.5 GB
563 financial-summarization-pegasus human-centered-summarization · summarization 570 M 512 unknown 148 K 3.1 GB
564 dreamshaper-8 Lykon · text-to-image 860 M — ⚠ creativeml-openrail-m 142 K 9.7 GB
565 one-obsession-17-red-sdxl John6666 · text-to-image 2.6 B — other 140 K 8.5 GB
566 Hunyuan-MT-7B-GGUF Mungert · translation — — unknown 137 K 3.1 GB
567 amanatsu-illustrious-v11-sdxl John6666 · text-to-image 2.6 B — other 135 K 8.5 GB
568 stable-diffusion-inpainting stable-diffusion-v1-5 · text-to-image — — ⚠ creativeml-openrail-m 128 K 3.5 GB
569 FLUX.1-schnell-gguf city96 · text-to-image — — ✓ apache-2.0 126 K 4.9 GB
570 LCM_Dreamshaper_v7 SimianLuo · text-to-image 860 M — ✓ mit 119 K 10.4 GB
571 FLUX.1-dev-gguf city96 · text-to-image — — other 109 K 4.9 GB
572 controlnet-union-sdxl-1.0 xinsir · text-to-image 1.3 B — ✓ apache-2.0 97 K 6.2 GB
573 Hy-MT2-1.8B tencent · translation 2.0 B 262 K ✓ apache-2.0 96 K 5.3 GB
574 stable-diffusion-v1-5 crynux-network · text-to-image 860 M — unknown 92 K 8.3 GB
575 T5-base-10K-summarization yatharth97 · summarization 220 M — unknown 84 K 1.5 GB
576 mbart-large-en-ro facebook · translation 610 M 1 K ✓ mit 82 K 1.9 GB
577 diving-illustrious-real-asian-v50-sdxl John6666 · text-to-image 2.6 B — other 81 K 8.5 GB
578 HunyuanDiT-v1.1-Diffusers-Distilled Tencent-Hunyuan · text-to-image 1.5 B — other 79 K 16.7 GB
579 Qwen-Image-2512-GGUF unsloth · text-to-image — — ✓ apache-2.0 77 K 8.6 GB
580 sdxl-turbo crynux-network · text-to-image — — ✓ apache-2.0 77 K 15.8 GB
581 picx-real GraydientPlatformAPI · text-to-image 860 M — ⚠ openrail 75 K 3.6 GB
582 sd-xl-alternative-bases benjamin-paine · text-to-image — — ⚠ openrail++ 73 K 15.9 GB
583 controlnet-openpose-sdxl-1.0 xinsir · text-to-image 1.3 B — ✓ apache-2.0 71 K 6.2 GB
584 Illustrious-xl-early-release-v0 OnomaAIResearch · text-to-image 2.6 B — other 69 K 23.8 GB
585 mbart-large-50-many-to-many-mmt facebook · translation 610 M 1 K unknown 69 K 3.3 GB
586 janku-v5-nsfw-trained-noobai-rou-wei-illustrious-xl-v50-sdxl John6666 · text-to-image 2.6 B — other 68 K 8.5 GB
587 hassaku-xl-illustrious-v31-sdxl John6666 · text-to-image 2.6 B — other 62 K 8.5 GB
588 Krea-2-Turbo-GGUF vantagewithai · text-to-image — — other 61 K 5.9 GB
589 obsession-illustriousxl-v10-sdxl John6666 · text-to-image 2.6 B — other 61 K 8.5 GB
590 sarvam-translate sarvamai · translation 4.3 B — gpl-3.0 60 K 10.6 GB
591 animagine-xl-3.0 cagliostrolab · text-to-image 2.6 B — ⚠ openrail++ 58 K 16.1 GB
592 lcm-lora-sdv1-5 latent-consistency · text-to-image — — ⚠ openrail++ 58 K 0.6 GB
593 Z-Image-Turbo-FP8 T5B · text-to-image — — ✓ apache-2.0 58 K 14.0 GB
594 noobai-XL-1.1 Laxhar · text-to-image 2.6 B — other 56 K 16.3 GB
595 InstantID InstantX · text-to-image — — ✓ apache-2.0 55 K 3.3 GB
596 Krea2_FP8 AlperKTS · text-to-image — — other 53 K 20.7 GB
597 controlnet-openpose-sdxl-1.0 thibaud · text-to-image — — other 51 K 6.9 GB
598 Z-Image-Turbo-GGUF unsloth · text-to-image — — ✓ apache-2.0 49 K 4.5 GB
599 ideogram-4-nf4 ideogram-ai · text-to-image · gated 4.8 B — other 45 K 18.9 GB
600 flux-klein-9b-Biglove-Collection Granddyser · text-to-image — — ✗ cc-by-nc-4.0 45 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.