Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
BoredomIsFun
30 days ago
|
parent
|
context
|
favorite
| on:
Why your local LLM feels dumber than it is
Llama 3.2 3B was surprisingly good for general-purpose text manipulation tasks. I'd argue it might be better than many modern tiny models for that.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
