Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
NexaQuant: Llama.cpp-Compatible Model Compression with 100%+ Accuracy Recovery
(
nexa.ai
)
3 points
by
BUFU
15 days ago
|
hide
|
past
|
favorite
|
1 comment
BUFU
15 days ago
[–]
Will llama.cpp be the go-to local inference framework for every device?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
