Benchmark result

qwen3.8-flash-next-iq3_xxs on AMD Radeon RX 6950 XT — 52.2 tok/s

Measured with Strata Strata (manual) on October 28, 2026.

What the model built

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 2 runs of this model on AMD Radeon RX 6950 XT · median 45.9 tok/s.

sort

152.2tok/s85.1Stratathis run
239.5tok/s70.5Strata

Compare the nearest 5 →

qwen3.8-flash-next-iq3_xxs on other hardware

Reproduce this run

toolStrata Strata (manual)

modelqwen3.8-flash-next-iq3_xxs

context131,072

thinkingon

effortxhigh

samplingtemperature 1 · top_p 0.95 · top_k 20

clientv0.4.98+102

Set those in Strata, then:

llm-benchmark benchmark --model "qwen3.8-flash-next-iq3_xxs" --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.