community-verified · measured pool data

Can the Radeon AI Pro R9700 32GB ×4 run DeepSeek-V4-Flash?

Yes — community-measured at 53.7 tok/s (2 runs at 2-bit).

Verified single-stream runs on the Radeon AI Pro R9700 32GB ×4 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
2-bit	53.7	5602	—	2,052	hipfire

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 →