community-verified · measured pool data

Can the Multi-GPU 48GB ×2 run Qwen3.5-27B-AWQ-BF16-INT4?

Yes — community-measured at 28.9 tok/s (2 runs at 4-bit).

Verified single-stream runs on the Multi-GPU 48GB ×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
4-bit 28.9 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 →