Benchmark result
qwen2.5:14b on Intel Graphics — 9.5 tok/s
Measured with Ollama 0.40.13 on November 1, 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
2nd fastest of 4 runs of this model on Intel Graphics · median 7.7 tok/s.
sort
- 110.3tok/s57.5Ollama
- 29.5tok/s56.8Ollama · Q4_K_Mthis run
- 35.9tok/s0.0Ollama · Q4_K_M
- 43.6tok/s53.6Ollama · Q4_K_M
Reproduce this run
toolOllama 0.40.13
modelqwen2.5:14b (Q4_K_M)
context8,192
clientv0.4.98+102
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen2.5:14b" --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.