Benchmark result
K2-Horizon-MoVA-36B-A4B-BF16-MLX on Apple M4 Max — 31.7 tok/s
Measured with oMLX 0.31.3 on September 12, 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
modelK2-Horizon-MoVA-36B-A4B-BF16-MLX
context262,144
kv cachenone
think limitnone
samplingtemperature 1 · top_p 0.95 · top_k 0 · repetition_penalty 1
clientv0.4.59+97
Set those in oMLX, then:
llm-benchmark benchmark --model "K2-Horizon-MoVA-36B-A4B-BF16-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.