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 2 × 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
$
739 models
#ModelParamsContextCommercial use30dOn 2 × 24 GB
601 LLaMmlein_1B_prerelease LSX-UniWue · text-generation 1.1 B 2 K other 179 K 5.5 GB
602 Pony_Diffusion_V6_XL LyliaEngine · text-to-image — — cdla-permissive-2.0 179 K 8.5 GB
603 Qwen3-1.7B-GGUF MaziyarPanahi · text-generation — — unknown 178 K 1.5 GB
604 Phi-3-mini-4k-instruct-gptq-4bit kaitchup · text-generation 3.8 B 4 K unknown 178 K 3.6 GB
605 Qwen3-32B-GGUF MaziyarPanahi · text-generation — — unknown 177 K 14.1 GB
606 Qwen3-30B-A3B-GGUF MaziyarPanahi · text-generation — — unknown 177 K 12.9 GB
607 Juggernaut-XL-v9 RunDiffusion · text-to-image — — ⚠ creativeml-openrail-m 176 K 15.9 GB
608 starcoder2-3b bigcode · text-generation 3.0 B 16 K bigcode-openrail-m 176 K 14.3 GB
609 Qwen3-30B-A3B-Thinking-2507-AWQ-4bit cyankiwi · text-generation 5.3 B 262 K ✓ apache-2.0 173 K 21.2 GB
610 avibe AvitoTech · text-generation 7.9 B 33 K ✓ apache-2.0 173 K 19.1 GB
611 llama-3-8b-instruct-awq casperhansen · text-generation 8.0 B 8 K unknown 173 K 8.0 GB
612 Qwen2.5-0.5B-Instruct-GGUF Qwen · text-generation — — ✓ apache-2.0 172 K 1.0 GB
613 NVIDIA-Nemotron-Nano-9B-v2-FP8 nvidia · text-generation 8.9 B 131 K other 171 K 13.1 GB
614 Qwen3-30B-A3B-FP8 Qwen · text-generation 30.5 B 41 K ✓ apache-2.0 171 K 40.8 GB
615 granite-4.1-3b-GGUF ibm-granite · text-generation — — ✓ apache-2.0 170 K 2.0 GB
616 Qwen3-14B-GPTQ-Int4 JunHowie · text-generation 14.8 B 41 K ✓ apache-2.0 170 K 13.7 GB
617 LFM2.5-8B-A1B LiquidAI · text-generation 8.5 B 128 K other 170 K 20.4 GB
618 falcon-mamba-7b tiiuae · text-generation 7.3 B — other 170 K 17.6 GB
619 Qwen2.5-7B-Instruct-bnb-4bit unsloth · text-generation 7.8 B 33 K ✓ apache-2.0 170 K 7.8 GB
620 TinyLlama-1.1B-Chat-v0.3-AWQ TheBloke · text-generation 1.1 B 2 K ✓ apache-2.0 169 K 1.5 GB
621 Meta-Llama-3-8B-Instruct NousResearch · text-generation 8.0 B 8 K other 169 K 19.4 GB
622 Gemma-4-26B-A4B-it-NVFP4 bg-digitalservices · text-generation 15.1 B — ✓ apache-2.0 168 K 20.8 GB
623 Meta-Llama-3.1-8B-Instruct-AWQ-INT4 hugging-quants · text-generation 8.0 B 131 K ⚠ llama3.1 167 K 8.0 GB
624 Qwen3-30B-A3B-GPTQ-Int4 Qwen · text-generation 30.5 B 41 K ✓ apache-2.0 167 K 23.7 GB
625 Agents-A1-4B InternScience · text-generation 4.5 B — ✓ apache-2.0 167 K 11.2 GB
626 Qwen2.5-Math-1.5B-Instruct Qwen · text-generation 1.5 B 4 K ✓ apache-2.0 167 K 4.1 GB
627 RnJ-1-Instruct-FP8 Doradus-AI · text-generation 8.8 B 33 K ⚠ gemma 164 K 15.0 GB
628 Llama-3.2-1B-Instruct-GGUF bartowski · text-generation — — ⚠ llama3.2 162 K 1.2 GB
629 Qwen3-4B-Instruct-2507-NVFP4 llmat · text-generation 2.8 B 262 K ✓ apache-2.0 161 K 4.9 GB
630 stable-diffusion-xl-1.0-inpainting-0.1 diffusers · text-to-image 2.6 B — ⚠ openrail++ 155 K 23.8 GB
631 opus-mt-tc-big-tr-en Helsinki-NLP · translation 230 M 1 K ✓ cc-by-4.0 154 K 1.1 GB
632 animagine-xl-3.1 cagliostrolab · text-to-image 2.6 B — ⚠ openrail++ 153 K 16.1 GB
633 nova-furry-xl-il-v120-sdxl John6666 · text-to-image 2.6 B — other 151 K 8.5 GB
634 financial-summarization-pegasus human-centered-summarization · summarization 570 M 512 unknown 148 K 3.1 GB
635 dreamshaper-8 Lykon · text-to-image 860 M — ⚠ creativeml-openrail-m 142 K 9.7 GB
636 one-obsession-17-red-sdxl John6666 · text-to-image 2.6 B — other 140 K 8.5 GB
637 Hunyuan-MT-7B-GGUF Mungert · translation — — unknown 137 K 3.1 GB
638 amanatsu-illustrious-v11-sdxl John6666 · text-to-image 2.6 B — other 135 K 8.5 GB
639 stable-diffusion-inpainting stable-diffusion-v1-5 · text-to-image — — ⚠ creativeml-openrail-m 128 K 3.5 GB
640 FLUX.1-schnell-gguf city96 · text-to-image — — ✓ apache-2.0 126 K 4.9 GB
641 LCM_Dreamshaper_v7 SimianLuo · text-to-image 860 M — ✓ mit 119 K 10.4 GB
642 FLUX.1-dev-gguf city96 · text-to-image — — other 109 K 4.9 GB
643 dreamshaper-xl-lightning Lykon · text-to-image 2.6 B — ⚠ openrail++ 100 K 39.0 GB
644 controlnet-union-sdxl-1.0 xinsir · text-to-image 1.3 B — ✓ apache-2.0 97 K 6.2 GB
645 Hy-MT2-1.8B tencent · translation 2.0 B 262 K ✓ apache-2.0 96 K 5.3 GB
646 stable-diffusion-v1-5 crynux-network · text-to-image 860 M — unknown 92 K 8.3 GB
647 RealVisXL_V4.0 SG161222 · text-to-image 2.6 B — ⚠ openrail++ 90 K 31.4 GB
648 T5-base-10K-summarization yatharth97 · summarization 220 M — unknown 84 K 1.5 GB
649 mbart-large-en-ro facebook · translation 610 M 1 K ✓ mit 82 K 1.9 GB
650 diving-illustrious-real-asian-v50-sdxl John6666 · text-to-image 2.6 B — other 81 K 8.5 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.