Benchmark result
Tiel-Coder-35B-A3B-MLX-oQ4e on Apple M5 Max — 54.5 tok/s
Measured with oMLX 0.31.4.dev132+g94cdcae13 on October 15, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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
7th fastest of 7 runs of this model on Apple M5 Max · median 112.7 tok/s.
sort
- 1121.4tok/s78.5oMLX
- 2120.2tok/s86.0oMLX
- 3119.1tok/s84.3oMLX
- 4112.7tok/s84.7oMLX
- 588.0tok/s82.1oMLX · oQ4e · KV none
- 665.9tok/s84.8oMLX
- 754.5tok/s84.7oMLX · oQ4e · KV nonethis run
Reproduce this run
tooloMLX 0.31.4.dev132+g94cdcae13
modelTiel-Coder-35B-A3B-MLX-oQ4e (oQ4e)
context131,072
kv cachenone
think limitnone
samplingtemperature 1 · top_p 0.95 · top_k 20 · repetition_penalty 1
clientv0.4.85+101
Set those in oMLX, then:
llm-benchmark benchmark --model "Tiel-Coder-35B-A3B-MLX-oQ4e" --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.