Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
vcryan
69 days ago
|
parent
|
context
|
favorite
| on:
Inkling: Our Open-Weights Model
I'm surprised that Nemotron gets mentioned at all. In my experiments with it for coding tasks it performed extremely poorly, essentially unusable.
jameshush
69 days ago
|
next
[–]
I focus on realtime voice AI uses cases and nemotron's time to first token is INSANELY fast. It's become a legit option for voice use cases
nostrebored
69 days ago
|
prev
[–]
it is pretty good at instruction following and has extremely fast decode.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: