Benchmark result
qwen_qwen3.5-4b@q8_0 on Apple M1 Max — 67.9 tok/s
Measured with LM Studio on November 3, 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 2 runs of this model on Apple M1 Max · median 68.4 tok/s.
sort
- 169.0tok/s73.0LM Studio · Q8_0
- 267.9tok/s66.7LM Studio · Q8_0this run
Reproduce this run
toolLM Studio
modelqwen_qwen3.5-4b@q8_0 (Q8_0)
context8,192
clientv0.4.98+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen_qwen3.5-4b@q8_0" --tool "LM Studio"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.