Benchmark result
qwen2.5-coder:7b-instruct on Apple M4 — 17.2 tok/s
Measured with Ollama 0.32.1 on July 17, 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
1st fastest of 2 runs of this model on Apple M4 · median 15.2 tok/s.
sort
- 117.2tok/s37.9Ollama · Q4_K_Mthis run
- 213.1tok/s51.3Ollama · Q4_K_M
Reproduce this run
toolOllama 0.32.1
modelqwen2.5-coder:7b-instruct (Q4_K_M)
context8,192
clientv0.4.29+97
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen2.5-coder:7b-instruct" --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.