Benchmark result
qwen3.8-flash-next-unsloth-ud-iq4_xs on NVIDIA GeForce RTX 4090 — 74.6 tok/s
Measured with Strata Strata (manual) on November 7, 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 5 runs of this model on NVIDIA GeForce RTX 4090 · median 68.6 tok/s.
sort
- 177.0tok/s84.3Strata
- 274.6tok/s85.9Stratathis run
- 368.6tok/s85.3Strata
- 460.0tok/s86.0Strata
- 550.8tok/s84.1Strata
qwen3.8-flash-next-unsloth-ud-iq4_xs on other hardware
Reproduce this run
toolStrata Strata (manual)
modelqwen3.8-flash-next-unsloth-ud-iq4_xs
context51,200
think limitnone
clientv0.4.98+102
Set those in Strata, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-unsloth-ud-iq4_xs" --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.