community-verified · measured pool data

Can the Arc Pro B70 32GB ×4 run DeepSeek-V4-Flash-180B?

Yes — community-measured at 41 tok/s (34 runs at 8-bit).

Verified single-stream runs on the Arc Pro B70 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
8-bit	41	330.2	—	1,024	vllm

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 →