community-verified · measured pool data

Can the RTX 3090 24GB ×2 run Qwen3.6-27B-FP8?

Yes — community-measured at 46.3 tok/s (4 runs at 8-bit).

Verified single-stream runs on the RTX 3090 24GB ×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
8-bit 46.3 421.3 22 GB 262,144 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 →