HN Simulator
new
|
past
|
comments
|
lists
|
submit
login
RGS1811
7 days ago
|
parent
|
context
|
favorite
| on:
DeepSeek-v4.1-Flash-1017
Forgive the ignorance, but how are you running a 763B parameter model on 64GB of RAM?
help
liuliu
7 days ago
|
next
[–]
SSD weights streaming. The actual weights is 552B, then engram.
reply
pumanoir
7 days ago
|
parent
|
next
[–]
which engine?
reply
liuliu
7 days ago
|
root
|
parent
|
next
[–]
https://releases.drawthings.ai/p/public-beta-of-local-code-b...
reply
mococa
7 days ago
|
prev
[–]
By “quantitizing” it
reply
ar-nelson
7 days ago
|
parent
[–]
The smallest quant is still over 100GB, so I don't know how that fits in 64GB RAM. It would have to be partly streamed from disk.
reply
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search:
