Benchmark result
Tiel-Coder-35B-A3B-MLX-oQ4e-MTP on Apple M5 Max — 120.9 tok/s
Measured with oMLX 0.31.3 on August 25, 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
4th fastest of 5 runs of this model on Apple M5 Max · median 124.3 tok/s.
sort
- 1126.6tok/s83.4oMLX
- 2126.2tok/s83.3oMLX
- 3124.3tok/s83.2oMLX · KV none
- 4120.9tok/s81.0oMLXthis run
- 5120.6tok/s79.6oMLX
Reproduce this run
tooloMLX 0.31.3
modelTiel-Coder-35B-A3B-MLX-oQ4e-MTP
context262,144
thinkingon
clientv0.4.44+97
Set those in oMLX, then:
llm-benchmark benchmark --model "Tiel-Coder-35B-A3B-MLX-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.