Hacker Times
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
johndough
43 days ago
|
parent
|
context
|
favorite
| on:
Kimi K3 exploited the latest Redis server
Why not? The model is 2.8T parameters with native MXFP4, which is 1400GB.
alightsoul
42 days ago
[–]
I would figure it needs a lot of kV cache and context size which can be much bigger than the model itself
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: