Benchmark result
qwen3.8-flash-next-iq3_xxs on AMD Radeon RX 9070/9070 XT/9070 GRE — 53.7 tok/s
Measured with Strata Strata (manual) on October 24, 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
2nd fastest of 3 runs of this model on AMD Radeon RX 9070/9070 XT/9070 GRE · median 53.7 tok/s.
sort
- 156.5tok/s87.9Strata v0.2.6
- 253.7tok/s85.5Stratathis run
- 335.4tok/s89.2Strata
qwen3.8-flash-next-iq3_xxs on other hardware
Reproduce this run
toolStrata Strata (manual)
modelqwen3.8-flash-next-iq3_xxs
context65,536
thinkingon
effortmedium
think limitnone
clientv0.4.97+102
Set those in Strata, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-iq3_xxs" --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.