Hi, currently have a spare GeForce 1060 lying around collecting dust.
Planning to use it with Ollama for self-hosting my own AI model or maybe even for AI training.
Problem is, none of my home lab devices have a compatible connection to the GPU’s GPIO. My current setup includes:
- Beelink MINI S12 Intel Alder Lake N100
- Raspberry Pi 5
- Le Potato AML-S905X-CC
- Pi Picos
Would like to hear about recommendations or experiences with external GPU docks that I can use to connect my GPU to my home lab setup, thanks.
2 Comments
Robin@lemmy.world · 4 pts · 1y
You won't get much use out of a 1060 for AI. Maybe some toy models to learn but even then you might run into limitations with the older CUDA version
GrumpyDuckling@sh.itjust.works · 4 pts · 1y
It would be cheaper and better to just build a small PC with parts from a few generations ago and that card is only worth $50 for a reason.