Benchmark result
qwen2.5:7b-instruct-q4_K_M on Intel Graphics — 19.3 tok/s
Measured with Ollama 0.40.13 on November 2, 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 Graphics · median 19.5 tok/s.
sort
- 120.1tok/s49.4Ollama · Q4_K_M
- 219.5tok/s39.4Ollama · Q4_K_M
- 319.3tok/s41.3Ollama · Q4_K_Mthis run
Reproduce this run
toolOllama 0.40.13
modelqwen2.5:7b-instruct-q4_K_M (Q4_K_M)
context128,000
clientv0.4.98+102
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen2.5:7b-instruct-q4_K_M" --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.