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 Mac M3 · 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
$
612 models
#ModelParamsContextCommercial use30dOn Mac M3 · 24 GB
201 gemma-4-26B-A4B-it-GGUF unsloth · image-text-to-text — — ✓ apache-2.0 952 K 11.4 GB
202 F5-TTS SWivid · text-to-speech — — ✗ cc-by-nc-4.0 946 K 5.0 GB
203 privacy-filter-nemotron-GGUF LocalAI-io · token-classification — — ✓ apache-2.0 944 K 2.3 GB
204 wav2vec2-xls-r-300m-ftspeech saattrupdan · ASR 320 M — other 944 K 1.9 GB
205 pubmedbert-base-embeddings NeuML · sentence-similarity 110 M 512 ✓ apache-2.0 941 K 1.0 GB
206 vit-base-nsfw-detector AdamCodd · image-classification 90 M — ✓ apache-2.0 937 K 0.9 GB
207 Qwen2.5-Coder-7B-Instruct-AWQ Qwen · text-generation 7.6 B 33 K ✓ apache-2.0 930 K 7.8 GB
208 Qwen3-4B-Instruct-2507-FP8 Qwen · text-generation 4.4 B 262 K ✓ apache-2.0 930 K 6.9 GB
209 rtdetr_r101vd_coco_o365 PekingU · object-detection 80 M — ✓ apache-2.0 911 K 0.9 GB
210 repeat unslothai · feature-extraction — — unknown 908 K 0.5 GB
211 dreamshaper-7 Lykon · text-to-image 860 M — ⚠ creativeml-openrail-m 900 K 9.7 GB
212 snowflake-arctic-embed-l-v2.0 Snowflake · sentence-similarity 570 M 8 K ✓ apache-2.0 889 K 3.1 GB
213 Juggernaut-XL-v9 RunDiffusion · text-to-image — — ⚠ creativeml-openrail-m 869 K 15.9 GB
214 Llama-3.2-1B meta-llama · text-generation · gated 1.2 B — ⚠ llama3.2 869 K 3.4 GB
215 ced-gguf mudler · audio-classification — — ✓ apache-2.0 866 K 0.6 GB
216 jina-embeddings-v2-small-en jinaai · feature-extraction 30 M 8 K ✓ apache-2.0 862 K 0.6 GB
217 Qwen2.5-1.5B Qwen · text-generation 1.5 B 131 K ✓ apache-2.0 860 K 4.1 GB
218 deberta-v3-base-prompt-injection-v2 protectai · text-classification 180 M 512 ✓ apache-2.0 852 K 1.3 GB
219 opus-mt-fr-en Helsinki-NLP · translation 80 M 512 ✓ apache-2.0 848 K 0.8 GB
220 wav2vec2-large-xlsr-mvc-swahili eddiegulay · ASR 320 M — ✓ apache-2.0 845 K 1.9 GB
221 e5-base-v2 intfloat · sentence-similarity 110 M 512 ✓ mit 829 K 1.0 GB
222 Qwen3-0.6B-Base Qwen · text-generation 600 M 33 K ✓ apache-2.0 816 K 1.9 GB
223 POCKET-35B-GGUF FINAL-Bench · text-generation — — ✓ apache-2.0 812 K 9.6 GB
224 Llama-2-7b-hf meta-llama · text-generation · gated 6.7 B — ⚠ llama2 806 K 16.3 GB
225 Ornith-1.5-9B-NVFP4 ornith-ai · text-generation 6.7 B — ✓ mit 805 K 11.2 GB
226 multi-qa-MiniLM-L6-cos-v1 sentence-transformers · sentence-similarity 20 M 512 unknown 805 K 0.6 GB
227 OLMo-2-0425-1B allenai · text-generation 1.5 B 4 K ✓ apache-2.0 799 K 7.3 GB
228 Qwen3.8-4B-Distill-GGUF empero-ai · text-generation — — ✓ apache-2.0 793 K 3.6 GB
229 Qwen3-8B-FP8 Qwen · text-generation 8.2 B 41 K ✓ apache-2.0 780 K 12.1 GB
230 rorshark-vit-base amunchet · image-classification 90 M — ✓ apache-2.0 777 K 0.9 GB
231 Qwen3.8-2B-Distill-GGUF empero-ai · text-generation — — ✓ apache-2.0 772 K 1.9 GB
232 efficientnet_b0.ra_in1k timm · image-classification 10 M — ✓ apache-2.0 761 K 0.5 GB
233 yolos-small hustvl · object-detection 30 M — ✓ apache-2.0 760 K 0.6 GB
234 pythia-6.9b EleutherAI · text-generation 7.0 B 2 K ✓ apache-2.0 754 K 16.8 GB
235 nemotron-3.5-asr-streaming-0.6b nvidia · ASR 640 M — other 752 K 1.4 GB
236 LaBSE sentence-transformers · sentence-similarity 470 M 512 ✓ apache-2.0 734 K 2.6 GB
237 bloomz-560m bigscience · text-generation 560 M — ⚠ bigscience-bloom-rail-1.0 724 K 1.8 GB
238 Kokoro-82M-v1.0-ONNX onnx-community · text-to-speech 82 M — ✓ apache-2.0 720 K 0.7 GB
239 ast-finetuned-audioset-10-10-0.4593 MIT · audio-classification 90 M — ✓ bsd-3-clause 719 K 0.9 GB
240 deepseek-coder-7b-instruct-v1.5 deepseek-ai · text-generation 6.9 B 4 K other 718 K 16.7 GB
241 Qwen3-14B-NVFP4 nvidia · text-generation 8.2 B 41 K ✓ apache-2.0 713 K 13.3 GB
242 wav2vec2-large-robust-12-ft-emotion-msp-dim audeering · audio-classification 170 M — ✗ cc-by-nc-sa-4.0 713 K 1.3 GB
243 Qwen2-0.5B Qwen · text-generation 490 M 131 K ✓ apache-2.0 709 K 1.7 GB
244 resnet50.ram_in1k timm · image-classification 30 M — ✓ apache-2.0 709 K 0.6 GB
245 gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-GGUF yuxinlu1 · text-generation — — ✓ apache-2.0 708 K 1.4 GB
246 e5-base intfloat · sentence-similarity 110 M 512 ✓ mit 701 K 1.0 GB
247 Qwen3.8-27B-DFlash2-GGUF z-lab · text-generation — — ✓ apache-2.0 696 K 1.8 GB
248 Giga-Embeddings-instruct ai-sage · feature-extraction 3.5 B — ✓ mit 695 K 16.2 GB
249 Qwen3.8-9B-Distill-GGUF empero-ai · text-generation — — ✓ apache-2.0 693 K 6.9 GB
250 bert-base-multilingual-uncased-sentiment nlptown · text-classification 170 M 512 ✓ mit 689 K 1.3 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.