Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dvt
on April 1, 2023
|
parent
|
context
|
favorite
| on:
Llama.cpp 30B runs with only 6GB of RAM now
This seems suspiciously like a bug (either in inference or in mmap reporting), as these models are not sparse enough for the savings to come from anywhere viable.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: