Benchmark result
mtplx-qwen38-27b-optimized-speed on Apple M4 Pro — 23.0 tok/s
Measured with MTPLX manual on October 14, 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
2nd fastest of 2 runs of this model on Apple M4 Pro · median 23.1 tok/s.
sort
- 123.3tok/s83.6MTPLX
- 223.0tok/s84.4MTPLXthis run
mtplx-qwen38-27b-optimized-speed on other hardware
Reproduce this run
toolMTPLX manual
modelmtplx-qwen38-27b-optimized-speed
context8,192
clientv0.4.93+102
Set those in MTPLX, then:
llm-benchmark benchmark --model "mtplx-qwen38-27b-optimized-speed" --tool "MTPLX"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.