Benchmark result

Qwen3.8-27B on NVIDIA GeForce RTX 3090 — 54.0 tok/s

Measured with Strata Strata (manual) on November 4, 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

3rd fastest of 12 runs of this model on NVIDIA GeForce RTX 3090 · median 50.5 tok/s.

sort

Compare the nearest 5 →

Qwen3.8-27B on other hardware

Reproduce this run

toolStrata Strata (manual)

modelQwen3.8-27B

context98,304

thinkingon

effortxhigh

think limitnone

samplingtemperature 1 · top_p 0.949999988079071 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1

clientv0.4.98+102

Set those in Strata, then:

llm-benchmark benchmark --model "Qwen3.8-27B" --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.