community-verified · measured pool data

Can the RTX 5090 32GB run Qwen3.6-27B-GGUF?

Yes — community-measured at 66.8 tok/s (6 runs at 4-bit).

Verified single-stream runs on the RTX 5090 32GB 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
3-bit	73.1	465.6	18.4 GB	131,072	llama.cpp
4-bit	66.8	455.5	19.5 GB	262,144	llama.cpp
5-bit	60.4	476	21.7 GB	131,072	llama.cpp
6-bit	50.9	523.2	24.6 GB	65,536	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 →