Benchmark result
nvidia/Qwen3.8-27B-NVFP4 on Apple M5 Max — 75.6 tok/s
Measured with OpenAI-compatible manual on October 16, 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 2 runs of this model on Apple M5 Max · median 75.5 tok/s.
sort
- 175.6tok/s73.6OpenAI-compatiblethis run
- 275.4tok/s76.7OpenAI-compatible
Reproduce this run
toolOpenAI-compatible manual
modelnvidia/Qwen3.8-27B-NVFP4
context131,072
clientv0.4.96+102
Set those in OpenAI-compatible, then:
llm-benchmark benchmark --model "nvidia/Qwen3.8-27B-NVFP4" --tool "OpenAI-compatible"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.