community-verified · measured pool data

Can the RTX 4090 24GB run Qwen3.6-27B-int4-AutoRound?

Yes — community-measured at 52.6 tok/s (2 runs at 16-bit).

Verified single-stream runs on the RTX 4090 24GB 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	52.6	87.8	—	2,048	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 →