Re:The $100B Megadeal Between OpenAI and Nvidia Is on Ice
by binary132 on Friday January 30, 2026 @10:47PM
(#46833225)
I find the Q8 runs a bit more than twice as fast as gpt-120b since I don’t have to offload as many MoE layers, but is just about as capable if not better.
[ Parent
| on HN ]
There are no comments on this comment yet.