Re:Ollama is now powered by MLX on Apple Silicon in preview
by ysleepy on Tuesday March 31, 2026 @04:16AM
(#47584198)
I'm actually not sure that's true. Apart from people buying the device with or without the neural accelerator, the perf/watt could be on par or better with the big iron. The efficiency sweet-spot is usually below the peak performance point, see big.little architectures etc.
[ Parent
| on HN ]
There are no comments on this comment yet.