Benchmark result
Laguna-S-2.1-NVFP4-mlx on Apple M5 Max — 36.6 tok/s
Measured with oMLX 0.31.3 on August 24, 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-S-2.1-NVFP4-mlx
context262,144
thinkingon
clientv0.4.43+97
Set those in oMLX, then:
llm-benchmark benchmark --model "Laguna-S-2.1-NVFP4-mlx" --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.