Benchmark result
qwen3.8-flash-next-unsloth-ud-q2_0 on AMD Radeon RX 7900 XT — 70.6 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
2nd fastest of 4 runs of this model on AMD Radeon RX 7900 XT · median 67.1 tok/s.
sort
- 170.6tok/s74.5Strata · Q2_0
- 270.6tok/s73.7Strata · Q2_0this run
- 363.6tok/s62.1Strata · Q2_0
- 461.8tok/s64.1Strata · Q2_0
Reproduce this run
toolStrata Strata (manual)
modelqwen3.8-flash-next-unsloth-ud-q2_0 (Q2_0)
context32,768
thinkingoff
clientv0.4.99+102
Set those in Strata, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-unsloth-ud-q2_0" --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.