Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
BoredomIsFun
39 days ago
|
parent
|
context
|
favorite
| on:
Muse Glimmer: 30B-parameter model optimized for al...
True, but local setups can run LLM requests in parallel too. In this case efficiency gap is much narrower.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
