Benchmark result
qwen3.8-flash-next-abliterated-iq3_s on AMD Radeon AI PRO R9700 — 58.7 tok/s
Measured with Strata Strata 0.1.43 on October 23, 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 3 runs of this model on AMD Radeon AI PRO R9700 · median 58.1 tok/s.
sort
- 158.7tok/s77.2Stratathis run
- 258.1tok/s79.6Strata
- 357.3tok/s85.5Strata
qwen3.8-flash-next-abliterated-iq3_s on other hardware
Reproduce this run
toolStrata Strata 0.1.43
modelqwen3.8-flash-next-abliterated-iq3_s
context8,192
thinkingoff
samplingtemperature 1 · top_p 0.95 · top_k 20
clientv0.4.97+102
Set those in Strata, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-abliterated-iq3_s" --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.