News for hackers. Stuff that matters.
Re:GPU-Accelerated LLM on a $100 Orange Pi by m00x on Tuesday August 15, 2023 @07:39PM (#37140830)
I think the biggest advantage here is that you can run it on the GPU using shared memory, which I'm not sure how widespread it is on mini PCs (at least not intel NUCs).

You could run it using OpenVINO on IntelCPUs, but the performance would probably take a hit. It would be a lot easier though since you can just use ggml.

There are no comments on this comment yet.