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

Can I run Gemma 4 31B on Apple M3 Ultra (80-core GPU)?

Yes — it runs.best quant:
Decode speed
30 tok/sest
Usable context
262K
Memory
512 GB
Fits in memory30 tok/sest · 262K ctx
Fits in memory26 tok/sest · 262K ctx
Fits in memory17 tok/sest · 262K ctx
What is quantisation? →
Gemma 4 31B
31.3B · full specs & benchmarks →
Apple M3 Ultra (80-core GPU)
512 GB · everything it runs →