Benchmark result
Ornith-1.5-35B-A3B-oQ4e-mtp on Apple M5 Max — 112.4 tok/s
Measured with oMLX 0.31.3 on September 11, 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.
How this run compares
3rd fastest of 4 runs of this model on Apple M5 Max · median 112.9 tok/s.
sort
- 1126.5tok/s82.9oMLX · oQ4e · KV none
- 2113.4tok/s85.0oMLX
- 3112.4tok/s86.7oMLX · KV nonethis run
- 4110.2tok/s85.7oMLX
Reproduce this run
tooloMLX 0.31.3
modelOrnith-1.5-35B-A3B-oQ4e-mtp
context262,144
kv cachenone
thinkingon
think limitnone
samplingtemperature 1 · top_p 0.95 · top_k 20 · 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.