community-verified · measured pool data

Can the Tesla P100 32GB ×2 run Qwen3.6-27B-GGUF?

Yes — community-measured at 17.2 tok/s (4 runs at 16-bit).

Verified single-stream runs on the Tesla P100 32GB ×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
16-bit	17.2	10078.5	—	2,048	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 →