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: Q4_K_M
Decode speed
29 tok/sest
Usable context
262K
Memory
512 GB
Q4_K_MFits in memory29 tok/sest · 262K ctx
Q5_K_MFits in memory25 tok/sest · 262K ctx
Q8_0Fits in memory17 tok/sest · 262K ctx
Gemma 4 31B
32.7B · full specs & benchmarks →
Apple M3 Ultra (80-core GPU)
512 GB · everything it runs →