oMLX on the M4 Pro 48GB
llamaperf has 3 oMLX reports on the M4 Pro 48GB, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.
3 oMLX reports on the M4 Pro 48GB
Newest first. A run on several cards, with speculative decoding, with part of the model in system RAM or with batched requests says so, since each describes a different setup.
- Qwen3.6 35B · 3B active · oQ490.0 t/s(speculative decoding)
- Qwen3.8 27B · oQ4e24.8 t/s(speculative decoding)
- GLM-5.3 · JANG1.8 t/s(speculative decoding)
Frequently asked
How fast is oMLX on the M4 Pro 48GB?
llamaperf has 3 oMLX reports on the M4 Pro 48GB, none of them a plain single-card run with a model size and quant, so there is no median to quote. The reports are listed below with how each one ran.