Benchmark result

qwen3.8-flash-next-iq3_s on NVIDIA GeForce RTX 3090 Ti — 115.6 tok/s

Measured with Strata Strata 0.1.47 on November 3, 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

qwen3.8-flash-next-iq3_s on other hardware

190.3tok/s88.4NVIDIA GeForce RTX 5090
121.7tok/s84.5NVIDIA GeForce RTX 5090
120.3tok/s82.72× NVIDIA GeForce RTX 3080
111.8tok/s79.9NVIDIA GeForce RTX 5090
89.2tok/s86.6NVIDIA GeForce RTX 3090

Reproduce this run

toolStrata Strata 0.1.47

modelqwen3.8-flash-next-iq3_s

context131,072

thinkingon

effortmedium

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_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.