Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
sanderjd
14 days ago
|
parent
|
context
|
favorite
| on:
Local Qwen isn't a worse Opus, it's a different to...
But that's current hardware. What about future hardware? What about hardware optimized for inference? What about hardware optimized to run a particular model?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
