Y
Hacker News
new
|
ask
|
show
|
jobs
user:
fatihturker
created:
2026-03-07
karma:
14
submissions:
0 points
|
0 comments
0 points
|
0 comments
Show HN: Efficient LLM Architectures for 32GB RAM (Ternary and Sparse Inference)
2 points
|
1 comments
Show HN: Run 500B+ Parameter LLMs Locally on a Mac Mini
17 points
|
10 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
Could ternary weights make 500B models runnable on consumer hardware?
7 points
|
6 comments
0 points
|
0 comments
0 points
|
0 comments
0 points
|
0 comments
Show HN: OpenGraviton – Run 500B+ parameter models on a consumer Mac Mini
13 points
|
5 comments