Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
antonvs
87 days ago
|
parent
|
context
|
favorite
| on:
Cerebras Code now supports GLM 4.6 at 1000 tokens/...
They claim they don't use quantization.
The reason for their speed is this chip:
https://www.cerebras.ai/chip
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
The reason for their speed is this chip: https://www.cerebras.ai/chip