Benchmark result

qwen3.8-27b-gsq-rco on Apple M5 Max — 43.8 tok/s

Measured with LM Studio on October 9, 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

1st fastest of 2 runs of this model on Apple M5 Max · median 36.9 tok/s.

sort

143.8tok/s84.6LM Studio · IQ3_Sthis run
229.9tok/s61.3LM Studio

Compare the nearest 5 →

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

Reproduce this run

toolLM Studio

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

context131,072

thinkingon

effortxhigh (model default)

clientv0.4.85+101

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.