AImodelsComparison.com 1,213 open · 210 API
Menu
Models Best of Trending Can I run it? Methodology MCP server About
1,423 models · 1,213 open weights · 210 API-only · refreshed nightly

Models that run on Mac M4 Max · 64 GB

Every model in the catalog — open weights you can self-host and API-only models — with licence or API price, estimated VRAM and daily-tracked downloads. Filters update the URL — share any view.

Type
All 1,423 Open weights (self-host) 1,213 API-only 210
Task
All text-generation 735 text-to-image 165 image-text-to-text 110 ASR 82 sentence-similarity 63 text-classification 50 translation 50 feature-extraction 46 image-classification 41 text-to-speech 23 token-classification 22 summarization 9 audio-classification 9 image-segmentation 9 object-detection 7 audio-text-to-text 1 any-to-any 1
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
$
871 models
#ModelParamsContextCommercial use30dOn Mac M4 Max · 64 GB
201 Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V10-GGUF LuffyTheFox · image-text-to-text Open weights — — ✓ apache-2.0 1.1 M 29.9 GB
202 Ornith-1.5-35B-A3B-NVFP4 ornith-ai · text-generation Open weights 19.5 B — ✓ mit 1.1 M 29.2 GB
203 wav2vec2-xls-r-300m-mixed mesolitica · ASR Open weights 300 M — unknown 1.1 M 1.2 GB
204 USER2-base deepvk · sentence-similarity Open weights 149 M 8 K ✓ apache-2.0 1.1 M 1.2 GB
205 filipino-wav2vec2-l-xls-r-300m-official Khalsuu · ASR Open weights 300 M — ✓ apache-2.0 1.1 M 1.2 GB
206 Qwen3-VL-2B-Instruct Qwen · image-text-to-text Open weights 2.1 B — ✓ apache-2.0 1.1 M 5.5 GB
207 wav2vec2-large-xls-r-300m-Urdu kingabzpro · ASR Open weights 320 M — ✓ apache-2.0 1.1 M 1.9 GB
208 Qwen3-Coder-30B-A3B-Instruct-FP8 Qwen · text-generation Open weights 30.5 B 262 K ✓ apache-2.0 1.1 M 39.4 GB
209 Muse-Glimmer-30B-GGUF unsloth · image-text-to-text Open weights — — ✓ apache-2.0 1.1 M 12.3 GB
210 bart-large-cnn facebook · summarization Open weights 410 M 1 K ✓ mit 1.1 M 2.3 GB
211 MiniCPM5-2B openbmb · text-generation Open weights 2.5 B 131 K ✓ apache-2.0 1.1 M 6.4 GB
212 bert-base-NER dslim · token-classification Open weights 110 M 512 ✓ mit 1.1 M 1.0 GB
213 Qwen3.8-Flash-Next-Gyro-abliterated-Huihui-GGUF agentionai · image-text-to-text Open weights — — other 1.1 M 3.5 GB
214 turn-detector livekit · text-classification Open weights 130 M 8 K other 1.1 M 1.1 GB
215 stable-diffusion-v1-5 stable-diffusion-v1-5 · text-to-image Open weights 860 M — ⚠ creativeml-openrail-m 1.0 M 26.6 GB
216 Breeze-TTS-2.cpp HoppouAI · text-to-speech Open weights — — other 1.0 M 3.3 GB
217 wav2vec2-xls-r-parlaspeech-hr classla · ASR Open weights 320 M — unknown 1.0 M 1.9 GB
218 animagine-xl-4.0 cagliostrolab · text-to-image Open weights 2.6 B — ⚠ openrail++ 1.0 M 23.8 GB
219 Qwen2-VL-2B-Instruct Qwen · image-text-to-text Open weights 2.2 B 33 K ✓ apache-2.0 1.0 M 5.7 GB
220 BiRefNet ZhengPeng7 · image-segmentation Open weights 220 M — ✓ mit 1.0 M 1.0 GB
221 Ternary-Bonsai-27B-mlx-2bit prism-ml · text-generation Open weights 2.6 B — ✓ apache-2.0 1.0 M 10.2 GB
222 jina-embeddings-v5-omni-small jinaai · feature-extraction Open weights 1.6 B — ✗ cc-by-nc-4.0 1.0 M 4.5 GB
223 e5-base-v2 intfloat · sentence-similarity Open weights 110 M 512 ✓ mit 1.0 M 1.0 GB
224 NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4 nvidia · text-generation Open weights 17.8 B 1.0 M other 1.0 M 26.9 GB
225 UAE-Large-V1 WhereIsAI · feature-extraction Open weights 340 M 512 ✓ mit 1.0 M 2.0 GB
226 Qwen3.8-27B-Turbo-Brilliance-50X-Reasoning-Instruct-NEO-MAX-MTP-GGUF DavidAU · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 1.0 M 14.2 GB
227 gemma-3-4b-it google · image-text-to-text · gated Open weights Also via API 4.3 B — ⚠ gemma 1.0 M 10.6 GB
228 Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V11-GGUF LuffyTheFox · image-text-to-text Open weights — — ✓ apache-2.0 1.0 M 29.9 GB
229 Bonsai-27B-mlx-1bit prism-ml · text-generation Open weights 1.7 B — ✓ apache-2.0 1.0 M 6.4 GB
230 Qwen3.8-27B-GGUF ggml-org · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 1.0 M 6.4 GB
231 wav2vec2-xls-r-300m-hebrew imvladikon · ASR Open weights 320 M — unknown 1.0 M 1.9 GB
232 parakeet-ultra-gguf handy-computer · ASR Open weights — — ✓ cc-by-4.0 1,000 K 1.0 GB
233 Qwen3.6-35B-A3B-Uncensored-Genesis-Hermes-V9-GGUF LuffyTheFox · image-text-to-text Open weights — — ✓ apache-2.0 998 K 29.8 GB
234 Ternary-Bonsai-2-2B-gguf prism-ml · image-text-to-text Open weights 2.0 B — ✓ apache-2.0 994 K 1.2 GB
235 Cyber-Tiel-Coder-35B-A3B-GGUF-MTP peculiar-ragdoll · image-text-to-text Open weights 35.0 B — ✓ mit 992 K 19.7 GB
236 wav2vec2-xls-r-300m-cv7-turkish mpoyraz · ASR Open weights 300 M — ✓ cc-by-4.0 991 K 1.2 GB
237 VoxCPM2 openbmb · text-to-speech Open weights 2.3 B — ✓ apache-2.0 987 K 5.9 GB
238 e5-small-v2 intfloat · sentence-similarity Open weights 30 M 512 ✓ mit 986 K 0.7 GB
239 MiMo-V2.6-Distill-Qwen-9B-GGUF bartowski · image-text-to-text Open weights 9.0 B — unknown 984 K 5.7 GB
240 sup-SimCSE-VietNamese-phobert-base VoVanPhuc · sentence-similarity Open weights 140 M 256 unknown 978 K 1.1 GB
241 surya-ocr-2 datalab-to · image-text-to-text Open weights 690 M — ⚠ openrail 975 K 2.1 GB
242 Qwen2.5-Coder-32B-Instruct-AWQ Qwen · text-generation Open weights 32.8 B 33 K ✓ apache-2.0 972 K 26.7 GB
243 Qwen3.8-27B-NVFP4 RadixArk · image-text-to-text Open weights 18.2 B — ✓ apache-2.0 969 K 27.3 GB
244 vietnamese-bi-encoder bkai-foundation-models · sentence-similarity Open weights 130 M 256 ✓ apache-2.0 968 K 1.1 GB
245 LaBSE sentence-transformers · sentence-similarity Open weights 470 M 512 ✓ apache-2.0 965 K 2.6 GB
246 InternVL2-1B OpenGVLab · image-text-to-text Open weights 940 M — ✓ mit 964 K 2.7 GB
247 Z-Image-Turbo-GGUF unsloth · text-to-image Open weights 6.2 B — ✓ apache-2.0 963 K 4.0 GB
248 1 unslothai · feature-extraction Open weights — 2 K unknown 963 K 0.5 GB
249 e5-base intfloat · sentence-similarity Open weights 110 M 512 ✓ mit 953 K 1.0 GB
250 Tess-4.5-27B-GGUF migtissera · image-text-to-text Open weights 27.0 B — ✓ apache-2.0 952 K 5.6 GB
VRAM figures are estimates for the smallest available quantization at 8K context — see /methodology. Downloads refresh nightly from the Hugging Face API; API prices (blended 3:1 input:output per 1M tokens) and Artificial Analysis indices from OpenRouter.