llamaperf

Qwen3.8 27B

on Unknown GPU · Gufo

Tone: positive
Nov 3, 2026
Throughput
30.0 t/s gen

Use cases

agentic

Summary

User reports Qwen3.8 27B running at around 30 t/s on long contexts in agentic work with the Gufo engine. No hardware, quant or context length is stated. The user says the latest versions of Gufo are impressive and get work done.

Compare this run

Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.

Qwen3.8 27B at 4-bit by hardware

Bars are medians on one scale, 0 to 94.0 tokens/s. Each dot is one run and opens its report. Press ▶ to watch text arrive at a row's speed.

Every Qwen3.8 report →