Benchmark result
qwen3.8-flash-next-iq3_s on Quadro RTX 5000 with Max-Q Design — 46.5 tok/s
Measured with strata 0.2.9 / engine 0.1.55 manual on November 2, 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
Reproduce this run
toolstrata 0.2.9 / engine 0.1.55 manual
modelqwen3.8-flash-next-iq3_s
context8,192
clientv0.4.98+102
Set those in strata 0.2.9 / engine 0.1.55, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-iq3_s" --tool "strata 0.2.9 / engine 0.1.55"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.