community-verified · measured pool data

Can the Radeon AI Pro R9700 32GB ×3 run gpt-oss-120b?

Yes — community-measured at 67.6 tok/s (11 runs at 16-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
16-bit 67.6 236.4 68.5 GB 1,589 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 →