community-verified · measured pool data

Can the Arc Pro B60 24GB ×2 run Llama-2-7b-hf?

Yes — community-measured at 34.8 tok/s (2 runs at 2-bit).

Verified single-stream runs on the Arc Pro B60 24GB ×2 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	34.8	366.9	—	4,096	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 →