Benchmark result
qwen3-coder:latest on Intel Arc B390 — 13.2 tok/s
Measured with Ollama 0.40.0 on October 8, 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.
How this run compares
3rd fastest of 3 runs of this model on Intel Arc B390 · median 14.0 tok/s.
sort
- 115.0tok/s58.2Ollama · Q4_K_M
- 214.0tok/s63.3Ollama · Q4_K_M
- 313.2tok/s67.4Ollama · Q4_K_Mthis run
qwen3-coder:latest on other hardware
Reproduce this run
toolOllama 0.40.0
modelqwen3-coder:latest (Q4_K_M)
context32,768
samplingtemperature 0.7 · top_p 0.8 · top_k 20 · repeat_penalty 1.05
clientv0.4.89+102
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen3-coder:latest" --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.