Looking forward to giving this a try. I have tried MLX using Rapid MLX however the LLM (Qwen) would always have hiccups and get stuck repeating itself.
Moving onto llama.cpp I was able to get faster tokens with MTP and a more reliable llm.
I wonder what other people's experiences are using MLX vs llama.cpp
FWIW on my M1 Max I have not really seen any advantage at all from MLX.
I am fully prepared to believe the benefits accrue more to the M3 and up (because of changes to the Apple Neural Engine).
But with the models I've tested, unless I am missing something, the performance of GGUFs in llama.cpp has been better in some cases.
I still have not had results from Gemma 4's MTP be really worth it, to be honest; but with the Qwen 3.6 MoE it is measurable. Maybe with newer kit it is more meaningful.
(There is every chance that the above is not the experience of anyone who really deeply knows what they are doing; it feels like I am a perpetual novice at this stuff)
Same here. Tried MLX twice at different times after reading the claims here but it always does considerably worse for me than llamacpp.