Benchmark result
qwen3.8-flash-next-coder-iq1_m on AMD Radeon RX 9070/9070 XT/9070 GRE — 43.3 tok/s
Measured with Strata Strata 0.1.39 on October 5, 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 2 runs of this model on AMD Radeon RX 9070/9070 XT/9070 GRE · median 52.7 tok/s.
sort
- 162.0tok/s86.4Strata v0.2.6
- 243.3tok/s84.0Stratathis run
qwen3.8-flash-next-coder-iq1_m on other hardware
Reproduce this run
toolStrata Strata 0.1.39
modelqwen3.8-flash-next-coder-iq1_m
context262,144
effortxhigh (model default)
clientv0.4.59+97
Set those in Strata, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-coder-iq1_m" --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.