Benchmark result
Tiel-Coder-35B-A3B-MLX-oQ6e-MTP on Apple M5 Max — 141.8 tok/s
Measured with oMLX 0.7.1.dev1 on October 17, 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
4th fastest of 9 runs of this model on Apple M5 Max · median 139.5 tok/s.
sort
- 1174.4tok/s80.5oMLX · oQ6e · KV none
- 2166.5tok/s86.3oMLX · oQ6e · KV none
- 3142.4tok/s81.8oMLX · oQ6e · KV none
- 4141.8tok/s86.6oMLX · oQ6e · KV nonethis run
- 5139.5tok/s80.2oMLX · oQ6e · KV none
- 6127.7tok/s81.6oMLX · oQ6e · KV tq8
- 7125.2tok/s71.7oMLX · oQ6e · KV none
- 8118.0tok/s82.2oMLX · oQ6e · KV tq8
- 9107.7tok/s81.0oMLX · oQ6e · KV none
Tiel-Coder-35B-A3B-MLX-oQ6e-MTP on other hardware
Reproduce this run
tooloMLX 0.7.1.dev1
modelTiel-Coder-35B-A3B-MLX-oQ6e-MTP (oQ6e)
context65,536
kv cachenone
think limitnone
samplingtemperature 0.6 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 0 · repetition_penalty 1
clientv0.4.92+102
Set those in oMLX, then:
llm-benchmark benchmark --model "Tiel-Coder-35B-A3B-MLX-oQ6e-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.