Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
lolinder
on June 3, 2025
|
parent
|
context
|
favorite
| on:
My AI skeptic friends are all nuts
They know that, but all accounts I've read acknowledge that the unified memory is worse than dedicated VRAM. It's just much better than running LLMs on CPU and the only way for a regular consumer to get to 64GB+ of graphical memory.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: