BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

Qwen 3.8 27B Reports Multi-Token Inference Speed

Sep 12, 2026

A reported test measured Qwen 3.8 27B at 17.1 tokens per second using multi-token prediction, with results dependent on hardware and runtime.

Read the original at inews.zoombangla.comOpens the publisher's site in a new tab

More in Open-weight & owned stack