Benchmark result
qwen3.8-flash-next-iq2_xs on AMD Radeon RX 9070/9070 XT/9070 GRE — 76.2 tok/s
Measured with Strata Strata (manual) on October 19, 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
3rd fastest of 5 runs of this model on AMD Radeon RX 9070/9070 XT/9070 GRE · median 76.2 tok/s.
sort
- 178.2tok/s84.1Strata
- 276.9tok/s85.9Strata
- 376.2tok/s85.9Stratathis run
- 471.4tok/s86.9Strata
- 545.7tok/s85.7Strata
qwen3.8-flash-next-iq2_xs on other hardware
Reproduce this run
toolStrata Strata (manual)
modelqwen3.8-flash-next-iq2_xs
context65,536
thinkingon
effortmedium
think limitnone
clientv0.4.96+102
Set those in Strata, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-iq2_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.