Skip to content

What can the Mac mini M4 32 GB run?

What fits on the Mac mini M4 32 GB
Text models: 265Visual models: 16Strongest first
Memory
32 GB unified
Bandwidth
120 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 32 GB, best first
ModelBest fitContextSpeedStrongest at
Qwen3.8 27B4-bit56K5.9 tok/sChat, Coding, Agents, Docs
Muse Glimmer 30B4-bit128K5.6 tok/sDocs
Qwen3.6 35B A3B3-bit152K47 tok/sChat, Coding, Agents, Docs
Gemma 4 31B4-bit20K5.1 tok/sChat, Coding, Agents, Docs
Gemma 4 26B A4B5-bit216K32 tok/sChat, Coding, Agents, Docs
Qwen3.5 9B8-bit256K10 tok/sChat, Coding, Agents, Docs
GLM-4.7 Flash4-bit36K40 tok/sChat, Coding, Agents
Gemma 4 12B8-bit256K7.5 tok/sChat, Coding, Docs
Nemotron 3.5 Lightning 30B A3B4-bit256K38 tok/sAgents, Docs
Qwen3.5 4B8-bit256K19 tok/sAgents, Docs
Devstral Small 2 24B5-bit20K5.8 tok/sCoding
LFM2.5 24B A2B6-bit64K45 tok/sAgents
Mistral Small 3.2 24B5-bit20K5.8 tok/sChat, Coding, Agents
Ministral 3 14B8-bit36K6.8 tok/sCoding, Agents, Docs
Gemma 4 E4B8-bit128K17 tok/sChat, Coding, Docs
gpt-oss 20BMXFP4128K34 tok/sAgents
Ministral 3 8B8-bit80K11 tok/sDocs
Gemma 4 E2B8-bit128K31 tok/sChat
Olmo 3.1 32B3-bit64K6.1 tok/sChat, Coding, Agents, Docs
Llama 3.1 8B8-bit88K12 tok/sChat, Coding, Agents, Docs
Qwen3 14B8-bit28K6.5 tok/sNot rated
Qwen3 VL 8B Instruct8-bit72K11 tok/sText and images
Qwen3 8B8-bit40K12 tok/sNot rated
Qwen2.5 7B Instruct8-bit32K13 tok/sNot rated
Qwen2.5 VL 7B Instruct8-bit125K12 tok/sText and images
Unlimited OCR8-bit32K71 tok/sReading documents
Qwen3 VL 4B Instruct8-bit104K20 tok/sText and images
Qwen3 1.7B8-bit40K41 tok/sNot rated
Qwen3 4B8-bit40K22 tok/sNot rated
Qwen3 32B3-bit16K6.1 tok/sNot rated
Qwen3 4B Instruct 25078-bit104K22 tok/sNot rated
Qwen3.6 27B4-bit56K5.9 tok/sText and images
Qwen2.5 Coder 14B Instruct8-bit24K6.5 tok/sCoding
Qwen2.5 VL 3B Instruct8-bit125K23 tok/sText and images
Qwen3 Coder 30B A3B Instruct4-bit24K40 tok/sCoding
Qwen3.5 27B4-bit56K5.9 tok/sText and images
Qwen3.5 35B A3B3-bit152K47 tok/sText and images
NVIDIA Nemotron 3 Nano 30B A3B BF164-bit256K38 tok/sNot rated
Qwen2.5 Coder 7B Instruct8-bit32K13 tok/sCoding
Mistral 7B Instruct V0.28-bit32K13 tok/sNot rated
Chandra OCR 28-bit256K17 tok/sReading documents
Qwen3 30B A3B4-bit24K40 tok/sNot rated
Qwen3 VL 2B Instruct8-bit160K40 tok/sText and images
Gemma 3 4B IT8-bit128K24 tok/sText and images
Qwen3 30B A3B Instruct 25074-bit24K40 tok/sNot rated
Llama 3.2 3B Instruct8-bit128K27 tok/sNot rated
Laguna XS.24-bit20K41 tok/sNot rated
OTel 2.0 LLM 31B IT4-bit20K5.1 tok/sNot rated
Qwen2.5 32B Instruct3-bit16K6.1 tok/sNot rated
MiniCPM V 4.7 35B A3B3-bit168K47 tok/sText and images
Qwen2.5 14B Instruct8-bit24K6.5 tok/sNot rated
Laguna XS 2.14-bit20K41 tok/sNot rated
Qwen3 1.7B Base8-bit32K48 tok/sNot rated
Diffusiongemma 26B A4B IT5-bit104K30 tok/sText and images
Qwen2.5 VL 32B Instruct3-bit16K6.0 tok/sText and images
Qwen2.5 Coder 32B Instruct3-bit16K6.1 tok/sCoding
Qwen2 VL 7B Instruct8-bit32K12 tok/sText and images
Ornith 1.5 9B8-bit256K10 tok/sNot rated
Unlimited OCR 28-bit128K71 tok/sReading documents
Granite 4.1 3B8-bit128K25 tok/sNot rated

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 265 are shown.

Image and video models

Image and video models that run on the Mac mini M4 32 GB
ModelBest fitPer outputStrongest at
Stable Diffusion XL 1.016-bit2.7 minImages
Z-Image Turbo16-bit3.9 minImages
FLUX.1 [dev]8-bit7.8 minImages
Qwen-Image 2.18-bit64 minImages
FLUX.3 Klein16-bit5.7 minImages
Wan2.2 I2V A14B4-bit25.4 hVideo
FLUX.2 [klein] 9B8-bit1.8 minImages
Wan2.1 I2V 14B4-bit25.4 hVideo
Wan 2.1 T2V-14B4-bit31.7 hVideo
Krea 2 Turbo8-bit7.7 minImages
Stable Diffusion 3.5 Large8-bit34 minImages
MOSS-Image16-bit42 minImages
Wan 2.2 TI2V-5B16-bit6.0 hVideo
MOSS Image Base16-bit42 minImages
Wan 2.2 A14B4-bit25.4 hVideo
HunyuanVideo 1.58-bit26.9 hVideo

Only just too big

These need up to a quarter more memory than the Mac mini M4 32 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 32 GB?

Of the open models we track, the strongest that run well on the Mac mini M4 32 GB are Qwen3.8 27B, Muse Glimmer 30B, Qwen3.6 35B A3B. 265 text models fit it in all.

Calculated from published specs, not benchmarked. All machines