Benchmark result
qwen3.8-flash-next-q2_0 on Apple M1 Max — 27.2 tok/s
Measured with Strata Strata 0.1.59-metal on November 16, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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 M1 Max · median 27.7 tok/s.
sort
- 128.2tok/s77.4Strata · Q2_0
- 227.2tok/s63.6Strata · Q2_0this run
Reproduce this run
toolStrata Strata 0.1.59-metal
modelqwen3.8-flash-next-q2_0 (Q2_0)
context8,192
thinkingon
effortxhigh (model default)
samplingtemperature 1 · top_p 0.95 · top_k 20
clientv0.4.99+102
Set those in Strata, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-q2_0" --tool "Strata"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.