Benchmark result
Laguna-XS-2.1-4bit on Apple M4 Max — 82.0 tok/s
Measured with oMLX 0.31.3 on August 20, 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.
Reproduce this run
tooloMLX 0.31.3
modelLaguna-XS-2.1-4bit
context65,536
clientv0.4.36+97
Set those in oMLX, then:
llm-benchmark benchmark --model "Laguna-XS-2.1-4bit" --tool "oMLX"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.