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
551 Agents-A1-4B-Q8_0-GGUF InternScience · text-generation — — ✓ apache-2.0 230 K 1.2 GB
552 Qwen3-0.6B-GGUF Qwen · text-generation 600 M 41 K ✓ apache-2.0 229 K 1.3 GB
553 Mistral-7B-Instruct-v0.3-AWQ solidrust · text-generation 7.3 B 33 K ✓ apache-2.0 229 K 6.2 GB
554 Yi-Coder-9B-Chat-GGUF MaziyarPanahi · text-generation — — unknown 227 K 2.7 GB
555 Qwen2.5-14B-Instruct-GPTQ-Int4 Qwen · text-generation 14.8 B 33 K ✓ apache-2.0 227 K 13.7 GB
556 Ornith-1.5-9B-MLX-6bit ornith-ai · text-generation 9.0 B — unknown 226 K 9.8 GB
557 Llama-3.2-3B-Instruct-GGUF unsloth · text-generation — 131 K ⚠ llama3.2 224 K 2.0 GB
558 Qwen2.5-1.5B-Instruct-GGUF Qwen · text-generation — — ✓ apache-2.0 224 K 1.3 GB
559 Qwen-Image-2512-GGUF unsloth · text-to-image — — ✓ apache-2.0 222 K 8.6 GB
560 hyenadna-medium-450k-seqlen-hf LongSafari · text-generation 28 M — ✓ bsd-3-clause 221 K 0.6 GB
561 Olmo-3-7B-Instruct-SFT allenai · text-generation 7.3 B 66 K ✓ apache-2.0 220 K 17.7 GB
562 Llama-2-7b-hf NousResearch · text-generation 6.7 B 4 K unknown 220 K 16.3 GB
563 Qwen3-14B-GGUF Qwen · text-generation — — ✓ apache-2.0 219 K 10.4 GB
564 CAJAL-4B Agnuxo · text-generation — — ✓ apache-2.0 219 K 3.5 GB
565 Llama-3.1-Nemotron-Nano-8B-v1 nvidia · text-generation 8.0 B 131 K other 218 K 19.4 GB
566 granite-4.1-8b ibm-granite · text-generation 8.8 B 131 K ✓ apache-2.0 218 K 21.2 GB
567 GLM-4.7-Flash-GGUF unsloth · text-generation — — ✓ mit 216 K 13.0 GB
568 Gemma-4-E4B-DECKARD-HERETIC-NVFP4 AEON-7 · text-generation 6.2 B — ⚠ gemma 216 K 12.6 GB
569 TinyLLama-v0 Maykeye · text-generation <0.1 M 2 K ✓ apache-2.0 215 K 0.5 GB
570 DeepSeek-R1-Distill-Llama-8B deepseek-ai · text-generation 8.0 B 131 K ✓ mit 215 K 19.4 GB
571 Qwen2-7B Qwen · text-generation 7.6 B 131 K ✓ apache-2.0 214 K 18.4 GB
572 wildguard allenai · text-generation · gated 7.3 B — ✓ apache-2.0 214 K 17.5 GB
573 Phi-3-mini-128k-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 214 K 9.5 GB
574 Qwen3-30B-A3B-GPTQ-Int4 Qwen · text-generation 30.5 B 41 K ✓ apache-2.0 208 K 23.7 GB
575 Qwen_Qwen3-Next-80B-A3B-Thinking-GGUF bartowski · text-generation — — ✓ apache-2.0 208 K 18.7 GB
576 Bielik-11B-v3.0-Instruct-awq speakleash · text-generation 11.3 B 33 K ✓ apache-2.0 208 K 9.0 GB
577 Qwen2.5-Math-1.5B Qwen · text-generation 1.5 B 4 K ✓ apache-2.0 208 K 4.1 GB
578 Qwen3.6-35B-A3B-DFlash z-lab · text-generation 390 M 262 K ✓ apache-2.0 208 K 1.4 GB
579 Qwen3Guard-Gen-4B Qwen · text-generation 4.4 B 33 K ✓ apache-2.0 207 K 10.9 GB
580 FLUX.1-schnell-gguf city96 · text-to-image — — ✓ apache-2.0 202 K 4.9 GB
581 indictrans2-en-indic-dist-200M ai4bharat · translation · gated 270 M — ✓ mit 191 K 1.7 GB
582 IP-Adapter-FaceID h94 · text-to-image — — unknown 185 K 1.5 GB
583 nllb-200-3.3B facebook · translation 3.3 B 1 K ✗ cc-by-nc-4.0 179 K 8.3 GB
584 animagine-xl-3.1 cagliostrolab · text-to-image 2.6 B — ⚠ openrail++ 170 K 16.1 GB
585 opus-mt-tc-big-tr-en Helsinki-NLP · translation 230 M 1 K ✓ cc-by-4.0 155 K 1.1 GB
586 LCM_Dreamshaper_v7 SimianLuo · text-to-image 860 M — ✓ mit 141 K 10.4 GB
587 nova-furry-xl-il-v120-sdxl John6666 · text-to-image 2.6 B — other 138 K 8.5 GB
588 opus-mt-tc-big-ko-en Helsinki-NLP · translation 210 M 1 K ✓ cc-by-4.0 136 K 1.0 GB
589 stable-diffusion-inpainting stable-diffusion-v1-5 · text-to-image — — ⚠ creativeml-openrail-m 126 K 3.5 GB
590 controlnet-union-sdxl-1.0 xinsir · text-to-image 1.3 B — ✓ apache-2.0 118 K 6.2 GB
591 noobai-XL-1.1 Laxhar · text-to-image 2.6 B — other 116 K 16.3 GB
592 controlnet-openpose-sdxl-1.0 xinsir · text-to-image 1.3 B — ✓ apache-2.0 109 K 6.2 GB
593 novaAnimeXL_ilV140 frankjoshua · text-to-image 2.6 B — unknown 108 K 16.1 GB
594 stable-diffusion-xl-1.0-inpainting-0.1 diffusers · text-to-image 2.6 B — ⚠ openrail++ 104 K 23.8 GB
595 mbart-large-en-ro facebook · translation 610 M 1 K ✓ mit 102 K 1.9 GB
596 Hy-MT2-1.8B tencent · translation 2.0 B 262 K ✓ apache-2.0 96 K 5.3 GB
597 Wan2.2-I2V_General-NSFW-LoRA lopi999 · text-to-image — — unknown 93 K 1.8 GB
598 lcm-lora-sdv1-5 latent-consistency · text-to-image — — ⚠ openrail++ 93 K 0.6 GB
599 nllb-200-1.3B facebook · translation 1.3 B 1 K ✗ cc-by-nc-4.0 93 K 3.6 GB
600 Z-Image-Turbo-FP8 T5B · text-to-image — — ✓ apache-2.0 92 K 14.0 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.