Benchmark result
qwen3.5-4b@q6_k on Apple M1 Max — 46.7 tok/s
Measured with LM Studio on November 3, 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
1st fastest of 2 runs of this model on Apple M1 Max · median 45.8 tok/s.
sort
- 146.7tok/s58.3LM Studio · Q6_Kthis run
- 245.0tok/s72.3LM Studio · Q6_K
Reproduce this run
toolLM Studio
modelqwen3.5-4b@q6_k (Q6_K)
context8,192
clientv0.4.98+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen3.5-4b@q6_k" --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.