Benchmark result
qwen3.8-flash-next-coder-iq1_m on NVIDIA GeForce RTX 3090 — 101.9 tok/s
Measured with Strata Strata 0.1.63 on November 21, 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 4 runs of this model on NVIDIA GeForce RTX 3090 · median 98.6 tok/s.
sort
- 1104.3tok/s85.7Strata
- 2101.9tok/s68.6Stratathis run
- 395.3tok/s87.4Strata
- 459.9tok/s85.1Strata
qwen3.8-flash-next-coder-iq1_m on other hardware
Reproduce this run
toolStrata Strata 0.1.63
modelqwen3.8-flash-next-coder-iq1_m
context8,192
effortxhigh (model default)
samplingtemperature 1 · top_p 0.95 · top_k 20
clientv0.4.99+102
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.