LLMap
Models /Gemma 4 31B /Can I run it?
Compatibility check

Can I run Gemma 4 31B on Apple M5 Max (32-core GPU)?

Yes — it runs.best quant:
Decode speed
17 tok/sest
Usable context
16K
Memory
64 GB
Fits in memory17 tok/sest · 16K ctx
Fits in memory15 tok/sest · 16K ctx
Fits in memory10 tok/sest · 8K ctx
What is quantisation? →
Gemma 4 31B
31.3B · full specs & benchmarks →
Apple M5 Max (32-core GPU)
64 GB · everything it runs →