AnalysisAI ModelsAugust 11, 2026

Qwen3.6 27B hits 366 t/s with NVFP4 on V100s

Community post reports 366 tokens/sec (single stream) for Qwen3.6 27B with NVFP4 quantization on V100 GPUs, following an earlier post showing 1000 t/s with the same model and hardware.

1 source

Daily brief

Get tomorrow's AI brief in your inbox

More stories today

Open the live feed