Benchmark result
qwen3.8-flash-next-unsloth-ud-iq4_xs on NVIDIA GeForce RTX 5090 +1 more — 49.3 tok/s
Measured with llama.cpp PolyStrata 0.1.45 on November 4, 2026.
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 NVIDIA GeForce RTX 5090 +1 more · Multi-GPU · median 52.4 tok/s.
sort
- 155.5tok/s89.1llama.cpp
- 249.3tok/s80.3llama.cppthis run
qwen3.8-flash-next-unsloth-ud-iq4_xs on other hardware
Reproduce this run
toolllama.cpp PolyStrata 0.1.45
modelqwen3.8-flash-next-unsloth-ud-iq4_xs
context262,000
effortxhigh (model default)
think limitnone
samplingtemperature 1 · top_p 0.95 · top_k 20
clientv0.4.98+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-unsloth-ud-iq4_xs" --tool "llama.cpp"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.