Re:Nativ: Run frontier open models locally on your Mac
by kzrdude on Monday July 20, 2026 @05:12PM
(#48984951)
If you go small enough it should be no problem. For example Gemma 4 E4B in Q6 or Q4 quantization should run well on your laptop. It shouldn't be too taxing, but would still want to eat 7-9 GB of VRAM or so.
Now that model is mostly useful for writing or chatting.
Now that model is mostly useful for writing or chatting.