Benchmark result
qwen3.6:27b-coding on AMD Radeon RX 9070/9070 XT/9070 GRE — 13.7 tok/s
Measured with Ollama 0.30.6 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
qwen3.6:27b-coding on other hardware
Reproduce this run
toolOllama 0.30.6
modelqwen3.6:27b-coding (Q4_K_M)
context8,192
thinkingon
samplingtemperature 0.6 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1
clientv0.4.99+102
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen3.6:27b-coding" --tool "Ollama"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.