Benchmark result
mtplx-qwen36-27b-optimized-speed-v2 on Apple M5 Max — 47.9 tok/s
Measured with vLLM on September 1, 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.
Reproduce this run
toolvLLM
modelmtplx-qwen36-27b-optimized-speed-v2
context128,000
thinkingon
clientv0.4.46+97
Set those in vLLM, then:
llm-benchmark benchmark --model "mtplx-qwen36-27b-optimized-speed-v2" --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.