Compatibility check
Can I run Gemma 4 31B on Apple M2 (10-core GPU)?
Partially — with CPU offload.best quant:
19.7 GB of weights, plus 3.8 GB for the software that runs it and the smallest conversation it can hold, comes to 23.5 GB against the 18 GB this 24 GB device leaves free.
Decode speed
—
Usable context
—
Memory
24 GB
Spills to system RAM
Too largeest
Too large
Plan B — rent it
Gemma 4 31B is hosted by 14 providers from $0.33 per 1M output tokens (DekaLLM).Compare providers →
