Re:Serving AI from the Basement – 192GB of VRAM Setup
by nrp on Sunday September 08, 2024 @02:25PM
(#41482096)
How are you finding 2b/3b quantized llama 405B? Is it behaving better than 8b or 16b llama 70B?
[ Parent
| on HN ]
There are no comments on this comment yet.