Alibaba's Qwen 27B model originally needs 60GB of RAM, but Prism ML used quantization to shrink it to 6GB, making it runnable on a Mac Mini. This compression technique makes large language models accessible to regular hardware.
There is a model from a Chinese Alibaba called Quen 27B. It's a 27 billion parameter model. What does that mean? It's like 60 gigabytes. And so you need 60 gigabytes of RAM to run it as default. They got it down to like—
So think of that, 60 gigabytes. That's 100— like, you can put that into a 96 gigabyte Mac Mini. But let's keep going. 25.
A team called Prism ML Got it down to 6. Same model. Same model. Just some sort of more efficiency.
Yeah, they got— they moved 6 gigabytes of RAM. So that's a MacBook Air or a Mac Neo, or I think they call it Neo, like the new
