Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
ryao
on June 2, 2025
|
parent
|
context
|
favorite
| on:
Why DeepSeek is cheap at scale but expensive to ru...
There is nothing big about Groq’s chips. Their individual chips have only 230 MB RAM. Unlike Cerebras, which can load multiple layers into a single chip, grok must divide a layer across many chips.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: