Compatibility check
Can I run Gemma 4 E2B it on Apple M4 Max (40-core GPU)?
Yes — it runs.best quant:
Decode speed
124 tok/sest
Usable context
262K
Memory
128 GB
Fits in memory124 tok/sest · 262K ctx
Fits in memory105 tok/sest · 262K ctx
Fits in memory71 tok/sest · 262K ctx