Benchmark result
qwen3.8-27b on Apple M5 Max — 23.3 tok/s
Measured with LM Studio on September 8, 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.
How this run compares
2nd fastest of 3 runs of this model on Apple M5 Max · median 23.3 tok/s.
sort
- 124.3tok/s85.3LM Studio
- 223.3tok/s84.4LM Studiothis run
- 314.9tok/s49.4LM Studio
Reproduce this run
toolLM Studio
modelqwen3.8-27b
context65,536
clientv0.4.55+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "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.