Benchmark result
unsloth/Qwen3-Coder-30B-A3B-Instruct:Q3_K_S on AMD Radeon RX 9070/9070 XT/9070 GRE — 60.1 tok/s
Measured with llama.cpp b10754-2459f68b5 on October 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.
Reproduce this run
toolllama.cpp b10754-2459f68b5
modelunsloth/Qwen3-Coder-30B-A3B-Instruct:Q3_K_S (Q3_K_S)
context32,768
think limitnone
samplingtemperature 0.800000011920929 · top_p 0.949999988079071 · top_k 40 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.87+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "unsloth/Qwen3-Coder-30B-A3B-Instruct:Q3_K_S" --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.