Benchmark result
qwen3.8-9b-distill-mlx@4bit on Apple M1 Max — 42.2 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
1st fastest of 2 runs of this model on Apple M1 Max · median 41.7 tok/s.
sort
- 142.2tok/s64.1LM Studio · 4bitthis run
- 241.1tok/s67.7LM Studio · 4bit
Reproduce this run
toolLM Studio
modelqwen3.8-9b-distill-mlx@4bit (4bit)
context65,536
clientv0.4.98+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen3.8-9b-distill-mlx@4bit" --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.