community-verified · measured pool data

Can the Ryzen AI Max 395 128GB run gemma-4-31B-it?

Yes — community-measured at 10.7 tok/s (2 runs at 4-bit).

Verified single-stream runs on the Ryzen AI Max 395 128GB from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.

Quantization	Median tok/s	TTFT (ms)	Peak VRAM	Max context tested	Engines
4-bit	10.7	—	25.4 GB	16,384	llama.cpp

Go deeper

I have a goal — find models that fit my use case → I have hardware — browse everything my rig can run → All machine × model answer pages →