Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
rjzzleep
on Nov 13, 2023
|
parent
|
context
|
favorite
| on:
Fast and Portable Llama2 Inference on the Heteroge...
Is there any detailed info on how a 4090 + ryzen 7840 compares to any of the new Apple offerings with 64GB or more unified RAM?
renewiltord
on Nov 13, 2023
[–]
No. You just have to try it. Anecdotally, I can fit a larger Llama on my M1 Max with 64 GiB than my 3090 with 24 GiB.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: