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

Can I run Gemma 4 31B on Apple M5 Max (40-core GPU)?

Yes — it runs.best quant: Q4_K_M
Decode speed
22 tok/sest
Usable context
66K
Memory
128 GB
Q4_K_MFits in memory22 tok/sest · 66K ctx
Q5_K_MFits in memory19 tok/sest · 66K ctx
Q8_0Fits in memory12 tok/sest · 33K ctx
Gemma 4 31B
32.7B · full specs & benchmarks →
Apple M5 Max (40-core GPU)
128 GB · everything it runs →