Benchmark result

IFM--K2-Horizon-MoVA-36B-A4B on Apple M4 Max — 31.7 tok/s

Measured with oMLX 0.31.3 on September 12, 2026.

What the model built

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

2nd fastest of 2 runs of this model on Apple M4 Max · median 31.8 tok/s.

sort

131.9tok/s65.7oMLX · KV none
231.7tok/s81.3oMLX · KV nonethis run

Compare the nearest 5 →

Reproduce this run

tooloMLX 0.31.3

modelIFM--K2-Horizon-MoVA-36B-A4B

context131,072

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 "IFM--K2-Horizon-MoVA-36B-A4B" --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.