AImodelsComparison.com 1,011 models
Menu
Models Best of Trending Can I run it? Methodology About
1,011 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 89 image-text-to-text 82 sentence-similarity 55 feature-extraction 47 translation 44 text-classification 39 image-classification 32 token-classification 22 text-to-speech 16 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
$
731 models
#ModelParamsContextCommercial use30dOn 2 × 24 GB
251 gemma-4-26B-A4B-it-QAT-MLX-4bit lmstudio-community · image-text-to-text 4.6 B — ✓ apache-2.0 914 K 18.4 GB
252 Qwen2.5-1.5B-Instruct-AWQ Qwen · text-generation 1.8 B 33 K ✓ apache-2.0 913 K 2.5 GB
253 Qwen3.6-27B-GPTQ-Pro-4bit groxaxo · image-text-to-text 27.4 B — ✓ apache-2.0 909 K 25.2 GB
254 UI-TARS-1.5-7B ByteDance-Seed · image-text-to-text 8.3 B 128 K ✓ apache-2.0 909 K 38.2 GB
255 Phi-tiny-MoE-instruct microsoft · text-generation 3.8 B 4 K ✓ mit 907 K 9.3 GB
256 Qwen3.6-27B-MLX-6bit lmstudio-community · image-text-to-text 6.4 B — ✓ apache-2.0 907 K 26.5 GB
257 opus-mt-fr-en Helsinki-NLP · translation 80 M 512 ✓ apache-2.0 900 K 0.8 GB
258 VoxCPM2 openbmb · text-to-speech 2.3 B — ✓ apache-2.0 900 K 5.9 GB
259 gte-large thenlper · sentence-similarity 340 M 512 ✓ mit 897 K 1.3 GB
260 gemma-4-26B-A4B-it-NVFP4 RedHatAI · image-text-to-text 15.1 B — ✓ apache-2.0 897 K 20.8 GB
261 dreamshaper-7 Lykon · text-to-image 860 M — ⚠ creativeml-openrail-m 895 K 9.7 GB
262 Qwen3.6-35B-A3B-GGUF unsloth · image-text-to-text — — ✓ apache-2.0 895 K 11.6 GB
263 Qwen3.6-27B-MLX-5bit lmstudio-community · image-text-to-text 5.5 B — ✓ apache-2.0 892 K 22.7 GB
264 multi-qa-MiniLM-L6-cos-v1 sentence-transformers · sentence-similarity 20 M 512 unknown 882 K 0.6 GB
265 OmniVoice k2-fsa · text-to-speech 610 M — unknown 877 K 4.2 GB
266 wav2vec2-large-xlsr-korean kresnik · ASR 320 M — ✓ apache-2.0 877 K 1.9 GB
267 pubmedbert-base-embeddings NeuML · sentence-similarity 110 M 512 ✓ apache-2.0 877 K 1.0 GB
268 Qwen3-8B-FP8 Qwen · text-generation 8.2 B 41 K ✓ apache-2.0 876 K 12.1 GB
269 deepseek-v4-gguf antirez · text-generation — — ✓ mit 875 K 4.7 GB
270 SmolLM3-3B HuggingFaceTB · text-generation 3.1 B 66 K ✓ apache-2.0 872 K 7.7 GB
271 wav2vec2-large-xls-r-300m-Urdu kingabzpro · ASR 320 M — ✓ apache-2.0 867 K 1.9 GB
272 Qwen2.5-1.5B Qwen · text-generation 1.5 B 131 K ✓ apache-2.0 863 K 4.1 GB
273 mamba-130m-hf state-spaces · text-generation 130 M — unknown 846 K 1.1 GB
274 Qwen2.5-1.5B-quantized.w8a8 RedHatAI · text-generation 1.8 B 33 K ✓ apache-2.0 839 K 3.2 GB
275 llama-nemotron-embed-1b-v2 nvidia · feature-extraction 1.2 B 131 K other 828 K 3.4 GB
276 text2vec-base-chinese shibing624 · sentence-similarity 100 M 512 ✓ apache-2.0 824 K 1.0 GB
277 gte-small thenlper · sentence-similarity 30 M 512 ✓ mit 823 K 0.6 GB
278 PP-DocLayoutV3_safetensors PaddlePaddle · object-detection 30 M — ✓ apache-2.0 822 K 0.7 GB
279 Llama-3.2-1B-Instruct-FP8 RedHatAI · text-generation 1.5 B 131 K ⚠ llama3.2 799 K 3.0 GB
280 Kimi-K3-DSpark RadixArk · text-generation 2.3 B 1.0 M unknown 798 K 5.8 GB
281 mimi kyutai · feature-extraction 100 M 8 K ✓ cc-by-4.0 798 K 0.9 GB
282 Flux2-Klein-9B-True-V2 wikeeyang · text-to-image — — other 792 K 6.8 GB
283 Llama-2-7b-hf meta-llama · text-generation · gated 6.7 B — ⚠ llama2 779 K 16.3 GB
284 vntl-llama3-8b-v2-gguf lmg-anon · translation — — ⚠ llama3 774 K 6.8 GB
285 phi-2 microsoft · text-generation 2.8 B 2 K ✓ mit 771 K 7.0 GB
286 F5-TTS SWivid · text-to-speech — — ✗ cc-by-nc-4.0 770 K 5.0 GB
287 pythia-70m-deduped EleutherAI · text-generation 100 M 2 K ✓ apache-2.0 769 K 0.7 GB
288 DeepSeek-R1-Distill-Qwen-14B deepseek-ai · text-generation 14.8 B 131 K ✓ mit 766 K 35.2 GB
289 NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 nvidia · text-generation 18.2 B 262 K other 765 K 24.5 GB
290 LaBSE sentence-transformers · sentence-similarity 470 M 512 ✓ apache-2.0 764 K 2.6 GB
291 w2v-xls-r-uk Yehor · ASR 320 M — ✓ apache-2.0 764 K 1.9 GB
292 Ternary-Bonsai-27B-gguf prism-ml · text-generation — — ✓ apache-2.0 761 K 1.2 GB
293 wav2vec2-xls-r-300m-hebrew imvladikon · ASR 320 M — unknown 757 K 1.9 GB
294 Llama-2-7b-chat-hf meta-llama · text-generation · gated 6.7 B — ⚠ llama2 753 K 16.3 GB
295 wav2vec2-large-robust-12-ft-emotion-msp-dim audeering · audio-classification 170 M — ✗ cc-by-nc-sa-4.0 751 K 1.3 GB
296 Qwen3-0.6B-Base Qwen · text-generation 600 M 33 K ✓ apache-2.0 749 K 1.9 GB
297 Qwen3.6-27B-Text-NVFP4-MTP sakamakismile · text-generation 16.7 B — ✓ apache-2.0 747 K 24.6 GB
298 yolos-small hustvl · object-detection 30 M — ✓ apache-2.0 746 K 0.6 GB
299 Qwen3-30B-A3B-Instruct-2507-AWQ-4bit cyankiwi · text-generation 5.3 B 262 K ✓ apache-2.0 744 K 21.2 GB
300 e5-small-v2 intfloat · sentence-similarity 30 M 512 ✓ mit 739 K 0.7 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.