Compatibility check
Can I run Gemma 4 E2B it on Apple M5 Max (32-core GPU)?
Yes — it runs.best quant:
Decode speed
104 tok/sest
Usable context
262K
Memory
64 GB
Fits in memory104 tok/sest · 262K ctx
Fits in memory89 tok/sest · 262K ctx
Fits in memory59 tok/sest · 262K ctx