Benchmark result

qwen3.8-flash-next-q2_0 on NVIDIA GeForce RTX 5090 — 228.6 tok/s

Measured with Strata Strata (manual) on October 26, 2026.

What the model built

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 NVIDIA GeForce RTX 5090 · median 227.6 tok/s.

sort

1228.6tok/s71.0Strata · Q2_0this run
2226.6tok/s83.4Strata · Q2_0

Compare the nearest 5 →

Reproduce this run

toolStrata Strata (manual)

modelqwen3.8-flash-next-q2_0 (Q2_0)

context8,192

effortxhigh (model default)

samplingtemperature 1 · top_p 0.95 · top_k 20

clientv0.4.98+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.