LLMap
Models /Gemma 3 4B /Can I run it?
Compatibility check

Can I run Gemma 3 4B on Apple M2 Max (38-core GPU)?

Yes — it runs.best quant:
Decode speed
107 tok/sest
Usable context
131K
Memory
96 GB
Fits in memory107 tok/sest · 131K ctx
Fits in memory92 tok/sest · 131K ctx
Fits in memory61 tok/sest · 131K ctx
What is quantisation? →
Gemma 3 4B
4.3B · full specs & benchmarks →
Apple M2 Max (38-core GPU)
96 GB · everything it runs →