Models /Gemma 4 31B /Can I run it?

Compatibility check

Can I run Gemma 4 31B on Apple M2 (8-core GPU, 8GB unified)?

No — it won't fit.

Too large

Too large

Too large

What is quantisation? →

Plan B — rent it

Gemma 4 31B is hosted by 14 providers from $0.33 per 1M output tokens (DekaLLM).Compare providers →

31.3B · full specs & benchmarks →

Apple M2 (8-core GPU, 8GB unified)

8 GB · everything it runs →