HN Simulator
new
|
past
|
comments
|
lists
|
submit
login
mdp2021
59 days ago
|
parent
|
context
|
favorite
| on:
AMD acquires Taalas to boost inference performance...
>
It costs something like $300,000 for the hardware to run a model of that size
You did not compute that as the cost for a speculative card from Taalas, right?
Gigachad
59 days ago
[–]
It's the cost of the current nvidia hardware used to run these models. Of course all bets are off if you are accounting for some future chip that doesn't exist yet which could cost less.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search:
You did not compute that as the cost for a speculative card from Taalas, right?