Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
oceanplexian
5 months ago
|
parent
|
context
|
favorite
| on:
Ask HN: How can ChatGPT serve 700M users when I ca...
I can’t speak to the Tesla stuff but I run an Epyc 7713 with a single 3090 and creatively splitting the model between GPU/8 channels of DDR4 I can do about 9 tokens per second on a q4 quant.
CamperBob2
5 months ago
[–]
Impressive. Is that a distillation, or the real thing?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: