Re:The Nvidia DGX Spark Is a Tiny 128GB AI Mini PC Made for ...
by captaindiego on Tuesday April 01, 2025 @08:23PM
(#43552621)
Are these just good for LLM inference or can they be used to train stuff like CV models too? (Let's say vs. a 5090 which is same ball.park price-wise)
[ Parent
| on HN ]
Re:The Nvidia DGX Spark Is a Tiny 128GB AI Mini PC Made for ...
by banderwidthdk on Wednesday April 02, 2025 @01:31AM
(#43553899)
From my experience LLM inference really, really likes memory bandwidth, which at 1.79 TB/s the 5090 has quite the lead on the APU's 273GB/s