When HN users recommended it
1 HN user recommended this in 2024, in one comment.
20072026
Each tall tick is one HN user's first recommendation. A short tick is the same user again. Click a tick to jump to the comment.
1 HN user recommended this in 2024, in one comment.
Each tall tick is one HN user's first recommendation. A short tick is the same user again. Click a tick to jump to the comment.
Yes, Ollama does support running on multiple GPUs. The best bang for your buck though is probably a Mac Studio for a couple reasons:
* Unified memory effectively will let you run much larger models without requiring you to add in more GPUs * GPUs will require loading the model from system memory which is always going to be slower than macOS w/ metal * Fitting multiple GPUs (especially 4090s) into a case is difficult, and motherboards that can support it are expensive (such as https://www.amazon.com/ASUS-Pro-WS-Motherboard-Server-Grade/...)
The one benefit of the 4090s is that it _should_ in theory be faster, but YMMV.