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 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 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
$
763 models
#ModelParamsContextCommercial use30dOn 2 × 24 GB
601 SmolLM2-1.7B HuggingFaceTB · text-generation 1.7 B 8 K ✓ apache-2.0 243 K 4.5 GB
602 h2ovl-mississippi-800m h2oai · text-generation 830 M — ✓ apache-2.0 242 K 2.4 GB
603 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark nvidia · text-generation 760 M 1.0 M other 241 K 2.1 GB
604 llama-7b huggyllama · text-generation 6.7 B 2 K other 241 K 16.3 GB
605 convnext_femto.d1_in1k timm · image-classification 10 M — ✓ apache-2.0 241 K 0.5 GB
606 pythia-410m EleutherAI · text-generation 510 M 2 K ✓ apache-2.0 241 K 1.6 GB
607 Qwen3-8B-FP8 nvidia · text-generation 8.2 B 41 K ✓ apache-2.0 240 K 12.1 GB
608 Vikhr-Nemo-12B-Instruct-R-21-09-24 Vikhrmodels · text-generation 12.3 B 1.0 M ✓ apache-2.0 239 K 30.8 GB
609 LLaDA-8B-Instruct GSAI-ML · text-generation 8.0 B — ✓ mit 239 K 19.3 GB
610 Mellum2-12B-A2.5B-Instruct-GGUF-Q8_0 JetBrains · text-generation — — ✓ apache-2.0 238 K 14.7 GB
611 Laguna-XS-2.1-GGUF poolside · text-generation — — openmdw-1.1 235 K 22.8 GB
612 TinyStories-1M roneneldan · text-generation 1.0 M 2 K unknown 232 K 0.5 GB
613 diffusiongemma-26B-A4B-it-NVFP4 nvidia · text-generation 14.4 B — ✓ apache-2.0 232 K 23.4 GB
614 Mistral-Small-24B-Instruct-2501-AWQ stelterlab · text-generation 23.6 B 33 K ✓ apache-2.0 232 K 19.7 GB
615 LLaDA2.0-mini inclusionAI · text-generation 16.3 B 33 K ✓ apache-2.0 230 K 38.7 GB
616 h2ovl-mississippi-2b h2oai · text-generation 2.2 B — ✓ apache-2.0 230 K 5.6 GB
617 Agents-A1-4B-Q8_0-GGUF InternScience · text-generation — — ✓ apache-2.0 230 K 1.2 GB
618 Qwen3-0.6B-GGUF Qwen · text-generation 600 M 41 K ✓ apache-2.0 229 K 1.3 GB
619 Mistral-7B-Instruct-v0.3-AWQ solidrust · text-generation 7.3 B 33 K ✓ apache-2.0 229 K 6.2 GB
620 Yi-Coder-9B-Chat-GGUF MaziyarPanahi · text-generation — — unknown 227 K 2.7 GB
621 Qwen2.5-14B-Instruct-GPTQ-Int4 Qwen · text-generation 14.8 B 33 K ✓ apache-2.0 227 K 13.7 GB
622 Ornith-1.5-9B-MLX-6bit ornith-ai · text-generation 9.0 B — unknown 226 K 9.8 GB
623 Llama-3.2-3B-Instruct-GGUF unsloth · text-generation — 131 K ⚠ llama3.2 224 K 2.0 GB
624 Qwen2.5-1.5B-Instruct-GGUF Qwen · text-generation — — ✓ apache-2.0 224 K 1.3 GB
625 Qwen-Image-2512-GGUF unsloth · text-to-image — — ✓ apache-2.0 222 K 8.6 GB
626 hyenadna-medium-450k-seqlen-hf LongSafari · text-generation 28 M — ✓ bsd-3-clause 221 K 0.6 GB
627 GLM-4.7-Flash-AWQ-4bit cyankiwi · text-generation 32.1 B 203 K ✓ mit 221 K 27.5 GB
628 Olmo-3-7B-Instruct-SFT allenai · text-generation 7.3 B 66 K ✓ apache-2.0 220 K 17.7 GB
629 Llama-2-7b-hf NousResearch · text-generation 6.7 B 4 K unknown 220 K 16.3 GB
630 automotive flywheel-ai · text-generation 34.7 B — ✓ apache-2.0 219 K 29.0 GB
631 Qwen3-14B-GGUF Qwen · text-generation — — ✓ apache-2.0 219 K 10.4 GB
632 CAJAL-4B Agnuxo · text-generation — — ✓ apache-2.0 219 K 3.5 GB
633 Llama-3.1-Nemotron-Nano-8B-v1 nvidia · text-generation 8.0 B 131 K other 218 K 19.4 GB
634 granite-4.1-8b ibm-granite · text-generation 8.8 B 131 K ✓ apache-2.0 218 K 21.2 GB
635 Qwen3.6-27B-NVFP4 nvidia · text-generation 18.2 B — ✓ apache-2.0 217 K 27.3 GB
636 GLM-4.7-Flash-GGUF unsloth · text-generation — — ✓ mit 216 K 13.0 GB
637 Gemma-4-E4B-DECKARD-HERETIC-NVFP4 AEON-7 · text-generation 6.2 B — ⚠ gemma 216 K 12.6 GB
638 TinyLLama-v0 Maykeye · text-generation <0.1 M 2 K ✓ apache-2.0 215 K 0.5 GB
639 DeepSeek-R1-Distill-Llama-8B deepseek-ai · text-generation 8.0 B 131 K ✓ mit 215 K 19.4 GB
640 Qwen2-7B Qwen · text-generation 7.6 B 131 K ✓ apache-2.0 214 K 18.4 GB
641 wildguard allenai · text-generation · gated 7.3 B — ✓ apache-2.0 214 K 17.5 GB
642 Phi-3-mini-128k-instruct microsoft · text-generation 3.8 B 131 K ✓ mit 214 K 9.5 GB
643 GLM-4.7-Flash-MLX-8bit lmstudio-community · text-generation 29.9 B 203 K ✓ mit 213 K 40.0 GB
644 Qwen3.5-35B-A3B-APEX-GGUF mudler · text-generation — — ✓ apache-2.0 208 K 28.4 GB
645 Qwen3-30B-A3B-GPTQ-Int4 Qwen · text-generation 30.5 B 41 K ✓ apache-2.0 208 K 23.7 GB
646 Qwen_Qwen3-Next-80B-A3B-Thinking-GGUF bartowski · text-generation — — ✓ apache-2.0 208 K 18.7 GB
647 DeepSeek-R1-Distill-Llama-70B-GGUF unsloth · text-generation — 131 K ⚠ llama3.3 208 K 29.5 GB
648 Bielik-11B-v3.0-Instruct-awq speakleash · text-generation 11.3 B 33 K ✓ apache-2.0 208 K 9.0 GB
649 Qwen2.5-Math-1.5B Qwen · text-generation 1.5 B 4 K ✓ apache-2.0 208 K 4.1 GB
650 Qwen3.6-35B-A3B-DFlash z-lab · text-generation 390 M 262 K ✓ apache-2.0 208 K 1.4 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.