Re:Nvidia DGX Spark encrypted firmware slows inference speed...
by petu on Wednesday November 04, 2026 @05:45AM
(#50363732)
There's good open weight models for now, labs could stop releasing them for whatever reason (assuming "good model" is a moving target).
Re:Nvidia DGX Spark encrypted firmware slows inference speed...
by bri3d on Wednesday November 04, 2026 @11:51AM
(#50368289)
There are plenty of both transformer and non-LLM "edge" models that aren't free and open - think anything that ships in consumer electronics. Vendors usually want this IP protected.
And, the same GPUs are run in datacenter, where there's a big insider risk that vendors want to mitigate with encrypted models (if you're Anthropic and you want AWS to host your models, you don't want 5000 or even 500 or even 50 AWS employees with access to your highly valuable/desirable model weights).
The consumer has access to free and open models for local use.
The supplier has better control and wider market to serve running the models in data centers.
Only way I can see encrypted models being widespread is if they are bundled as part of a software package (OS/Browser/etc) and not sold as the product.