Benchmark result
local-qwen on AMD Radeon RX 7900 XTX — 60.5 tok/s
Measured with llama.cpp manual on September 26, 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.
How this run compares
1st fastest of 2 runs of this model on AMD Radeon RX 7900 XTX · median 60.2 tok/s.
sort
- 160.5tok/s85.7llama.cppthis run
- 260.0tok/s86.1llama.cpp
Reproduce this run
toolllama.cpp manual
modellocal-qwen
context16,000
effortxhigh (model default)
samplingtemperature 0.20000000298023224 · top_p 0.949999988079071 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1
clientv0.4.80+98
Set those in llama.cpp, then:
llm-benchmark benchmark --model "local-qwen" --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.