This one has mistakes though.. The ANE definitely exists in the m5 and has more tflops than the m4 or m3 version.
It sucks
I've got qwen 3.8 flash next and qwen 3.8 27b working on the ANE - 4 tok/s decode and 40 tok/s for 27b and 80 tok/s with 15-20tok/s decode for flash next.
This one has mistakes though.. The ANE definitely exists in the m5 and has more tflops than the m4 or m3 version.
It sucks
I've got qwen 3.8 flash next and qwen 3.8 27b working on the ANE - 4 tok/s decode and 40 tok/s for 27b and 80 tok/s with 15-20tok/s decode for flash next.