Benchmark result
qwen3.8-flash-next-unsloth-ud-iq4_xs on 2× NVIDIA GeForce RTX 3080 — 86.5 tok/s
Measured with Strata Strata 0.1.55 on November 2, 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 2× NVIDIA GeForce RTX 3080 · Multi-GPU · median 83.8 tok/s.
sort
- 186.5tok/s84.7Stratathis run
- 281.1tok/s84.7Strata
qwen3.8-flash-next-unsloth-ud-iq4_xs on other hardware
Reproduce this run
toolStrata Strata 0.1.55
modelqwen3.8-flash-next-unsloth-ud-iq4_xs
context262,144
thinkingon
effortmedium
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-unsloth-ud-iq4_xs" --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.