community-verified · measured pool data

Can the Ryzen AI Max 395 128GB run Qwopus3.5-27B-v3?

Yes — community-measured at 12.9 tok/s (5 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	12.9	—	17.5 GB	32,768	llama.cpp
5-bit	11.3	—	19.9 GB	32,768	llama.cpp
6-bit	9.9	—	23.5 GB	32,768	llama.cpp
8-bit	7.9	—	29.2 GB	32,768	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 →