Benchmark result

Ornith-1.5-35B-A3B-oQ4e-mtp on Apple M4 Pro — 68.7 tok/s

Measured with oMLX 0.6.4 on September 17, 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

7th fastest of 7 runs of this model on Apple M4 Pro · median 70.6 tok/s.

sort

Compare the nearest 5 →

Ornith-1.5-35B-A3B-oQ4e-mtp on other hardware

Reproduce this run

tooloMLX 0.6.4

modelOrnith-1.5-35B-A3B-oQ4e-mtp

context65,536

kv cachenone

think limitnone

samplingtemperature 1 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 1.5 · repetition_penalty 1

clientv0.4.59+97

Set those in oMLX, then:

llm-benchmark benchmark --model "Ornith-1.5-35B-A3B-oQ4e-mtp" --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.