Skip to content

What can the Mac mini M4 Pro 64 GB run?

What fits on the Mac mini M4 Pro 64 GB
Text models: 181Visual models: 20Strongest first
Memory
64 GB unified
Bandwidth
273 GB/s
Maker
Apple

Open the calculator on this machine

Text models that run on it

Text models that run on the Mac mini M4 Pro 64 GB, best first
ModelBest fitContextSpeedStrongest at
Qwen3.8 27B8-bit256K7.6 tok/sChat, Coding, Agents, Docs
Muse Glimmer 30B8-bit128K7.2 tok/sDocs
Qwen3.5 122B A10B2-bit40K41 tok/sChat, Coding, Agents, Docs
Nemotron 3 Super 120B A12B2-bit208K30 tok/sChat, Coding, Agents, Docs
Nemotron 3.5 Bolt 74B A9B4-bit256K27 tok/sChat, Coding, Agents, Docs
Qwen3.6 35B A3B8-bit256K50 tok/sChat, Coding, Agents, Docs
Gemma 4 31B8-bit256K6.5 tok/sChat, Coding, Agents, Docs
Gemma 4 26B A4B8-bit256K45 tok/sChat, Coding, Agents, Docs
GLM-4.7 Flash8-bit198K48 tok/sChat, Coding, Agents
Gemma 4 12B8-bit256K17 tok/sChat, Coding, Docs
Mistral Small 4 119B2-bit144K63 tok/sChat, Docs
gpt-oss 120B2-bit112K74 tok/sChat, Coding
Qwen3 Coder Next 80B3-bit256K73 tok/sCoding, Agents
Nemotron 3.5 Lightning 30B A3B8-bit256K46 tok/sAgents, Docs
Devstral Small 2 24BFP8128K8.7 tok/sCoding
LFM2.5 24B A2B8-bit128K66 tok/sAgents
Mistral Small 3.2 24B8-bit128K8.8 tok/sChat, Coding, Agents
Ministral 3 14B8-bit192K15 tok/sCoding, Agents, Docs
gpt-oss 20BMXFP4128K67 tok/sAgents
Ministral 3 8B8-bit256K24 tok/sDocs
Llama 3.3 70B4-bit16K5.1 tok/sChat, Coding, Agents, Docs
Olmo 3.1 32B8-bit64K6.4 tok/sChat, Coding, Agents, Docs
Llama 3.1 8B8-bit128K26 tok/sChat, Coding, Agents, Docs
Qwen3 14B8-bit40K14 tok/sNot rated
Qwen3 VL 8B Instruct8-bit256K24 tok/sText and images
Qwen3 8B8-bit40K26 tok/sNot rated
Qwen3 32B8-bit40K6.4 tok/sNot rated
Qwen3.6 27B8-bit256K7.6 tok/sText and images
Qwen2.5 Coder 14B Instruct8-bit32K14 tok/sCoding
Qwen3 Coder 30B A3B Instruct8-bit152K48 tok/sCoding
Qwen3.5 27B8-bit256K7.6 tok/sText and images
Qwen3.5 35B A3B8-bit256K50 tok/sText and images
NVIDIA Nemotron 3 Nano 30B A3B BF168-bit256K46 tok/sNot rated
GLM 4.5 Air2-bit32K32 tok/sNot rated
Qwen3 30B A3B8-bit40K48 tok/sNot rated
Qwen3 30B A3B Instruct 25078-bit152K48 tok/sNot rated
Laguna XS.28-bit256K50 tok/sNot rated
OTel 2.0 LLM 31B IT8-bit256K6.5 tok/sNot rated
Qwen2.5 32B Instruct8-bit32K6.4 tok/sNot rated
MiniCPM V 4.7 35B A3B8-bit256K50 tok/sText and images
Qwen2.5 14B Instruct8-bit32K14 tok/sNot rated
Laguna XS 2.18-bit256K50 tok/sNot rated
Diffusiongemma 26B A4B IT8-bit256K43 tok/sText and images
Qwen2.5 VL 32B Instruct8-bit44K6.2 tok/sText and images
Qwen2.5 Coder 32B Instruct8-bit32K6.4 tok/sCoding
Laguna S 2.12-bit80K48 tok/sNot rated
Qwen3 VL 30B A3B Instruct8-bit144K48 tok/sText and images
EXAONE 3.5 7.8B Instruct8-bit32K27 tok/sNot rated
DeepSeek R1 0528 Qwen3 8B8-bit128K26 tok/sNot rated
Gemma 3 12B IT8-bit128K18 tok/sText and images
Phi 3.5 Mini Instruct8-bit104K49 tok/sNot rated
DeepSeek R1 Distill Qwen 32B8-bit48K6.4 tok/sNot rated
Gemma 3 27B IT8-bit128K7.8 tok/sText and images
Ornith 1.5 35B A3B8-bit256K50 tok/sNot rated
Ornith 1.5 122B2-bit40K35 tok/sNot rated
GPT Neox 20B8-bit2K10.0 tok/sNot rated
Apertus 8B Instruct 25098-bit64K26 tok/sNot rated
Phi 48-bit16K14 tok/sNot rated
Phi 3 Mini 128K Instruct8-bit104K49 tok/sNot rated
Qwen3 VL 32B Instruct8-bit44K6.3 tok/sText and images

Best fit is the highest quality, up to 8-bit, that leaves the use case’s context. Ranked by our use-case scores, then by Hugging Face downloads. Speeds are rough, plus or minus 25%. The top 60 of 181 are shown.

Image and video models

Image and video models that run on the Mac mini M4 Pro 64 GB
ModelBest fitPer outputStrongest at
MiniMax H34-bit2.4 hVideo
LTX-2.58-bit13 minVideo
Z-Image Turbo16-bit1.9 minImages
FLUX.1 [dev]16-bit3.9 minImages
Qwen-Image8-bit75 minImages
FLUX.2 [dev]5-bit38 minImages
Qwen-Image 2.116-bit32 minImages
FLUX.3 Klein16-bit2.9 minImages
Wan2.2 I2V A14B16-bit11.0 hVideo
FLUX.2 [klein] 9B16-bit55 sImages
Wan2.1 I2V 14B16-bit11.0 hVideo
Wan 2.1 T2V-14B16-bit13.8 hVideo
Krea 2 Turbo16-bit3.9 minImages
Stable Diffusion 3.5 Large16-bit17 minImages
Qwen Image 25128-bit75 minImages
MOSS-Image16-bit21 minImages
Wan 2.2 TI2V-5B16-bit3.0 hVideo
MOSS Image Base16-bit21 minImages
Wan 2.2 A14B16-bit11.0 hVideo
HunyuanVideo 1.516-bit13.5 hVideo

Only just too big

These need up to a quarter more memory than the Mac mini M4 Pro 64 GB has. Spilling into system RAM or a lower precision can get them running, slowly.

Questions

What is the best LLM for the Mac mini M4 Pro 64 GB?

Of the open models we track, the strongest that run well on the Mac mini M4 Pro 64 GB are Qwen3.8 27B, Muse Glimmer 30B, Qwen3.5 122B A10B. 181 text models fit it in all.

Calculated from published specs, not benchmarked. All machines