This would have been a great edition for the Strix Halo had it been released last year. Not now with the RAM crunch drastically inflating prices and it costing close to Nvidia's DGX Spark. The one benefit it has over the Spark is it's AMD, not ARM, so you can also use it as general purpose computer, not just an AI host.
I am very curious about how the "threat" of local inference and open-weights-models will change the trajectory of the model labs. The air will become pretty thin
This would have been a great edition for the Strix Halo had it been released last year. Not now with the RAM crunch drastically inflating prices and it costing close to Nvidia's DGX Spark. The one benefit it has over the Spark is it's AMD, not ARM, so you can also use it as general purpose computer, not just an AI host.
I am very curious about how the "threat" of local inference and open-weights-models will change the trajectory of the model labs. The air will become pretty thin
the threat is non-existing for agentic flows. Local interfere could catch up on high end phones