Benchmark result
qwen3.8-flash-next-unsloth-ud-q5_k_xl on AMD Radeon RX 7900 XTX — 49.3 tok/s
Measured with llama.cpp PolyStrata 0.1.45 on November 11, 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 7900 XTX · median 51.7 tok/s.
sort
- 154.1tok/s81.5llama.cpp · Q5_K
- 249.3tok/s81.5llama.cpp · Q5_Kthis run
Reproduce this run
toolllama.cpp PolyStrata 0.1.45
modelqwen3.8-flash-next-unsloth-ud-q5_k_xl (Q5_K)
context65,536
effortxhigh (model default)
think limitnone
samplingtemperature 1 · top_p 0.95 · top_k 20
clientv0.4.99+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-unsloth-ud-q5_k_xl" --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.