Benchmark result
qwen2.5-coder:latest on Intel Arc B390 — 18.4 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
2nd fastest of 3 runs of this model on Intel Arc B390 · median 18.4 tok/s.
sort
- 118.5tok/s42.6Ollama · Q4_K_M
- 218.4tok/s39.2Ollama · Q4_K_Mthis run
- 318.4tok/s26.8Ollama · Q4_K_M
Reproduce this run
toolOllama 0.40.0
modelqwen2.5-coder:latest (Q4_K_M)
context32,768
clientv0.4.89+102
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen2.5-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.