community-verified · measured pool data

Can the Radeon AI Pro R9700 57GB run Qwen3.6-35B-A3B?

Yes — community-measured at 26.4 tok/s (2 runs at 6-bit).

Verified single-stream runs on the Radeon AI Pro R9700 57GB 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
6-bit	26.4	1567.7	—	2,048	llama.cpp
8-bit	24.4	1253.8	—	2,048	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 →