Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jauntywundrkind
5 days ago
|
parent
|
context
|
favorite
| on:
IBM CEO says open weight models are now good and c...
Intel Crescent Lake is dropping. 1.4TB/s of LPDDR5X, up to 480GB. It's not going to be cheap but it's much better than trying to buy gddr based cards.
Still (as bit over) 1/2 the ram bus width of a single HBM4 stack though! (1280b vs 2048b).
help
jacquesm
5 days ago
[–]
That's going to be pretty pricey though. And I really want to see some independent benchmarks, that all looks very good on paper but there are some complications (notably: chip count, run length of the traces).
reply
Consider applying for YC's Winter 2027 batch!
Applications
are open till November 2.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
Still (as bit over) 1/2 the ram bus width of a single HBM4 stack though! (1280b vs 2048b).