Benchmark result
qwen3.5:latest — 69.5 tok/s
Measured with Ollama 0.30.6 on July 29, 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
qwen3.5:latest on other hardware
- 69.5tok/s39.6Unknown hardware · Q4_K_Mthis run
- 35.9tok/s25.8Apple M4 Pro · Q4_K_M
- 15.1tok/s64.0Intel Arc B390 · Q4_K_M
- 15.0tok/s57.5Intel Arc B390 · Q4_K_M
- 15.0tok/s61.5Intel Arc B390 · Q4_K_M
Reproduce this run
toolOllama 0.30.6
modelqwen3.5:latest (Q4_K_M)
context8,192
clientv0.4.30+97
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen3.5: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.