community-verified · measured pool data

Can the M3 Ultra 512GB run Qwen3.6-27B?

Yes — community-measured at 26.3 tok/s (3 runs at 4-bit).

Verified single-stream runs on the M3 Ultra 512GB 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
4-bit 26.3 316.2 8,192 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 →