Benchmark result
mlx-community/Qwen3.8-27B-4bit on Apple M5 Max — 82.2 tok/s
Measured with vLLM on October 10, 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 10 runs of this model on Apple M5 Max · median 30.6 tok/s.
sort
Compare the nearest 5 →
Reproduce this run
toolvLLM
modelmlx-community/Qwen3.8-27B-4bit
context131,072
effortxhigh (model default)
clientv0.4.85+101
Set those in vLLM, then:
llm-benchmark benchmark --model "mlx-community/Qwen3.8-27B-4bit" --tool "vLLM"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.