Benchmark result
qwen3.8-flash-next-unsloth-ud-iq4_xs-v31 on AMD Radeon RX 7900 XT — 44.0 tok/s
Measured with Strata Strata (manual) on November 17, 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
1st fastest of 3 runs of this model on AMD Radeon RX 7900 XT · median 43.7 tok/s.
sort
- 144.0tok/s86.5Stratathis run
- 243.7tok/s81.5Strata
- 341.1tok/s85.8Strata
qwen3.8-flash-next-unsloth-ud-iq4_xs-v31 on other hardware
Reproduce this run
toolStrata Strata (manual)
modelqwen3.8-flash-next-unsloth-ud-iq4_xs-v31
context65,536
thinkingon
effortmedium
think limitnone
clientv0.4.99+102
Set those in Strata, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-unsloth-ud-iq4_xs-v31" --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.