Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
monkmartinez
8 days ago
|
parent
|
context
|
favorite
| on:
ChatGPT Pro
Memory. I don't know the equation, but its very easy to see when you load a 128k context model at 8K vs 80K. The quant I am running would double VRAM requirements when loading 80K.
thomasfromcdnjs
8 days ago
[–]
This was my understanding too. Would love more people to chime in on the limits and costs of larger contexts.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
