community-verified · measured pool data

Can the Radeon AI Pro R9700 32GB ×3 run qwen3-coder-30b-a3b-codemonkey?

Yes — community-measured at 126.8 tok/s (2 runs at 4-bit).

Verified single-stream runs on the Radeon AI Pro R9700 32GB ×3 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	126.8	201.3	—	786	llama.cpp
8-bit	85.2	124.7	—	794	llama.cpp
16-bit	20.5	146.4	—	786	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 →