Benchmark result
qwen/qwen3.8-27b on Apple M5 Max — 31.0 tok/s
Measured with LM Studio on October 4, 2026.
What the model built
Open full screen →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 5 runs of this model on Apple M5 Max · median 23.3 tok/s.
sort
- 131.0tok/s77.6LM Studio · 4bitthis run
- 224.3tok/s85.3LM Studio
- 323.3tok/s84.4LM Studio
- 417.8tok/s86.4LM Studio
- 514.9tok/s49.4LM Studio
Reproduce this run
toolLM Studio
modelqwen/qwen3.8-27b (4bit)
context65,536
thinkingon
effortlow
clientv0.4.87+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen/qwen3.8-27b" --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.