Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
Aissen
on April 24, 2024
|
parent
|
context
|
favorite
| on:
Snowflake Arctic Instruct (128x3B MoE), largest op...
How much memory would inference take on this type of model? What's the impact of it being an MoE architecture?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
