Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
johnisgood
on Dec 24, 2024
|
parent
|
context
|
favorite
| on:
GPT-5 is behind schedule
What are the hardware and software requirements for a self-hosted LLM that is akin to Claude?
skirmish
on Dec 26, 2024
[–]
Llama v3.3 70B after quantization runs reasonably well on a 24GB GPU (7900XTX or 4090) and 64GB of regular RAM. Software:
https://github.com/ggerganov/llama.cpp
.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
