Benchmark result

qwen3.8-27b-gsq-rco on AMD Radeon RX 9060 XT — 25.2 tok/s

Measured with LM Studio on October 14, 2026.

What the model built

The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.

How this run compares

2nd fastest of 2 runs of this model on AMD Radeon RX 9060 XT · median 37.3 tok/s.

sort

149.5tok/s81.6LM Studio
225.2tok/s72.8LM Studio · IQ3_Sthis run

Compare the nearest 5 →

qwen3.8-27b-gsq-rco on other hardware

Reproduce this run

toolLM Studio

modelqwen3.8-27b-gsq-rco (IQ3_S)

context16,384

thinkingoff

clientv0.4.93+102

Set those in LM Studio, then:

llm-benchmark benchmark --model "qwen3.8-27b-gsq-rco" --tool "LM Studio"

The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.