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

Can I run Gemma 4 31B on Apple M2 Ultra (76-core GPU)?

Yes — it runs.best quant:
Decode speed
30 tok/sest
Usable context
66K
Memory
192 GB
Fits in memory30 tok/sest · 66K ctx
Fits in memory25 tok/sest · 66K ctx
Fits in memory17 tok/sest · 66K ctx
What is quantisation? →
Gemma 4 31B
31.3B · full specs & benchmarks →
Apple M2 Ultra (76-core GPU)
192 GB · everything it runs →