Is it time to move to open source and run model locally with an DGX Spark?
Every single open source model I've used is nowhere close to as good as the big AI companies. They are about 2 years behind or more and unreliable. I'm using the large parameters ones on a 512GB Mac Studio and the results are still poor.
[dead]
alt Hacker News
Every single open source model I've used is nowhere close to as good as the big AI companies. They are about 2 years behind or more and unreliable. I'm using the large parameters ones on a 512GB Mac Studio and the results are still poor.