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
$
611 models
#ModelParamsContextCommercial use30dOn Mac M3 · 24 GB
151 distiluse-base-multilingual-cased-v2 sentence-transformers · sentence-similarity 130 M 512 ✓ apache-2.0 1.2 M 1.1 GB
152 nb-wav2vec2-1b-nynorsk NbAiLab · ASR 960 M — ✓ apache-2.0 1.2 M 4.9 GB
153 Qwen3.8-27B-GSQ-RCO-GGUF ISTA-DASLab · image-text-to-text — — ✓ apache-2.0 1.2 M 1.5 GB
154 LFM2.5-2.6B-GGUF LiquidAI · text-generation — — other 1.2 M 2.3 GB
155 surya-ocr-2 datalab-to · image-text-to-text 690 M — ⚠ openrail 1.2 M 2.1 GB
156 PowerMoE-3b ibm-research · text-generation 3.4 B 4 K ✓ apache-2.0 1.2 M 15.9 GB
157 whisper-tiny Xenova · ASR 40 M — ✓ apache-2.0 1.2 M 0.6 GB
158 pythia-70m-deduped EleutherAI · text-generation 100 M 2 K ✓ apache-2.0 1.2 M 0.7 GB
159 Qwen3.8-27B-GGUF ggml-org · image-text-to-text 27.0 B — ✓ apache-2.0 1.2 M 6.4 GB
160 Qwen2.5-Coder-14B-Instruct-AWQ Qwen · text-generation 14.8 B 33 K ✓ apache-2.0 1.1 M 13.7 GB
161 Qwen3.6-27B-MTP-GGUF unsloth · image-text-to-text — — ✓ apache-2.0 1.1 M 14.3 GB
162 wav2vec2-xls-r-300m-bengali arijitx · ASR 300 M — ✓ apache-2.0 1.1 M 1.2 GB
163 Qwen3-VL-Embedding-2B Qwen · sentence-similarity 2.1 B — ✓ apache-2.0 1.1 M 5.5 GB
164 wav2vec2-xls-r-parlaspeech-hr classla · ASR 320 M — unknown 1.1 M 1.9 GB
165 medgemma-4b-it google · image-text-to-text · gated 4.3 B — other 1.1 M 10.6 GB
166 Qwen3.6-27B-GGUF unsloth · image-text-to-text — — ✓ apache-2.0 1.1 M 14.1 GB
167 clipseg-rd64-refined CIDAS · image-segmentation 150 M — ✓ apache-2.0 1.1 M 1.2 GB
168 surya-ocr-2-gguf datalab-to · image-text-to-text — — ⚠ openrail 1.1 M 1.9 GB
169 UAE-Large-V1 WhereIsAI · feature-extraction 340 M 512 ✓ mit 1.1 M 2.0 GB
170 robertuito-sentiment-analysis pysentimiento · text-classification 110 M 128 unknown 1.1 M 1.0 GB
171 fairface_age_image_detection dima806 · image-classification 90 M — ✓ apache-2.0 1.1 M 2.4 GB
172 Muse-Glimmer-30B-GGUF unsloth · image-text-to-text — — ✓ apache-2.0 1.1 M 12.3 GB
173 Bonsai-27B-mlx-1bit prism-ml · text-generation 1.7 B — ✓ apache-2.0 1.1 M 6.4 GB
174 PP-DocLayoutV3_safetensors PaddlePaddle · object-detection 30 M — ✓ apache-2.0 1.1 M 0.7 GB
175 gte-small thenlper · sentence-similarity 30 M 512 ✓ mit 1.1 M 0.6 GB
176 Ternary-Bonsai-27B-mlx-2bit prism-ml · text-generation 2.6 B — ✓ apache-2.0 1.1 M 10.2 GB
177 parakeet-tdt-0.6b-v2 mlx-community · ASR 620 M — ✓ cc-by-4.0 1.1 M 3.3 GB
178 table-transformer-structure-recognition microsoft · object-detection 30 M 1 K ✓ mit 1.1 M 0.6 GB
179 bge-micro-v2 TaylorAI · sentence-similarity 20 M 512 ✓ mit 1.0 M 0.5 GB
180 Qwen3.6-35B-A3B-MTP-GGUF unsloth · image-text-to-text — — ✓ apache-2.0 1.0 M 13.0 GB
181 Llama-3.1-8B-Instruct-4bit mlx-community · text-generation 1.3 B 131 K ⚠ llama3.1 1.0 M 5.7 GB
182 1 unslothai · feature-extraction — 2 K unknown 1.0 M 0.5 GB
183 nb-wav2vec2-1b-bokmaal-v2 NbAiLab · ASR 960 M — ✓ apache-2.0 1.0 M 4.9 GB
184 nllb-200-distilled-600M facebook · translation 600 M 1 K ✗ cc-by-nc-4.0 1.0 M 1.9 GB
185 e5-mistral-7b-instruct-bnb-4bit gabor-hosu · feature-extraction 7.3 B 33 K ✓ mit 1.0 M 5.8 GB
186 Qwen3-TTS-12Hz-0.6B-CustomVoice Qwen · text-to-speech 910 M — ✓ apache-2.0 1.0 M 3.4 GB
187 distiluse-base-multilingual-cased-v1 sentence-transformers · sentence-similarity 130 M 512 ✓ apache-2.0 1.0 M 1.1 GB
188 glm-4-9b-chat-IMat-GGUF legraphista · text-generation — — other 1.0 M 3.9 GB
189 w2v-xls-r-uk Yehor · ASR 320 M — ✓ apache-2.0 1.0 M 1.9 GB
190 distilbert-base-multilingual-cased-sentiments-student lxyuan · text-classification 140 M 512 ✓ apache-2.0 1.0 M 1.1 GB
191 gte-large-en-v1.5 Alibaba-NLP · sentence-similarity 430 M 8 K ✓ apache-2.0 1.0 M 2.5 GB
192 JiRackUltra_14b CMSManhattan · text-generation 14.8 B 131 K ✓ mit 1.0 M 9.1 GB
193 BiRefNet ZhengPeng7 · image-segmentation 220 M — ✓ mit 998 K 1.0 GB
194 text2vec-base-chinese shibing624 · sentence-similarity 100 M 512 ✓ apache-2.0 995 K 1.0 GB
195 Qwen3.5-9B-AWQ QuantTrio · image-text-to-text 9.7 B — ✓ apache-2.0 984 K 15.6 GB
196 turn-detector livekit · text-classification 130 M 8 K other 978 K 1.1 GB
197 endless-frontier_BigBang-v1-GGUF bartowski · image-text-to-text — — ✓ apache-2.0 978 K 11.8 GB
198 wav2vec2-large-xlsr-korean kresnik · ASR 320 M — ✓ apache-2.0 971 K 1.9 GB
199 roberta-base-go_emotions SamLowe · text-classification 120 M 512 ✓ mit 962 K 1.1 GB
200 cohere-transcribe-03-2026-gguf handy-computer · ASR — — ✓ apache-2.0 961 K 2.2 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API.