Benchmark result
Qwen3.8-27B-Q5-XYZ-v2 on AMD Radeon RX 7900 XTX — 59.9 tok/s
Measured with llama.cpp b385-407f323 on September 9, 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.
Reproduce this run
toolllama.cpp b385-407f323
modelQwen3.8-27B-Q5-XYZ-v2
context65,536
thinkingon
clientv0.4.46+97
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Qwen3.8-27B-Q5-XYZ-v2" --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.