Re:Gemini 2.0: our new AI model for the agentic era
by griomnib on Wednesday December 11, 2024 @12:18PM
(#42390123)
Latency is a huge factor in performance, and local models often have a huge edge. Especially on mobile devices that could be offline entirely.
[ Parent
| on HN ]
Re:Gemini 2.0: our new AI model for the agentic era
by KoolKat23 on Thursday December 12, 2024 @04:38AM
(#42397703)
Definitely not when it comes to LLM's, the larger more useful local models are not that fast and latency is not an issue, just look at this Google models voice function or even openai's advanced voice.