community-verified · measured pool data

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

Yes — community-measured at 35.3 tok/s (2 runs at 2-bit).

Verified single-stream runs on the Arc Pro B60 24GB 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 35.3 367.5 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 →