community-verified · measured pool data

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

Yes — community-measured at 70.1 tok/s (7 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 73.5 35.9 13.5 GB 8,192 llama.cpp
4-bit 70.1 36.8 20 GB 243,040 llama.cpp, vllm
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 →