Benchmark result
Ling-3.0-tiny-oQ8e on Apple M4 Max — 121.9 tok/s
Measured with oMLX 0.31.3 on September 10, 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
2nd fastest of 3 runs of this model on Apple M4 Max · median 121.9 tok/s.
sort
- 1137.8tok/s56.5oMLX · KV tq8
- 2121.9tok/s56.0oMLX · KV tq8this run
- 3118.2tok/s63.4oMLX · KV tq8
Ling-3.0-tiny-oQ8e on other hardware
Reproduce this run
tooloMLX 0.31.3
modelLing-3.0-tiny-oQ8e
context131,072
kv cachetq8
efforthigh
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 "Ling-3.0-tiny-oQ8e" --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.