HN
Paper
All
Show
Ask
Jobs
Top
Today
Last 7 days
Last months
This year
Statistics
All
Show
Ask
Jobs
Top stories
Today
Last 7 days
Last months
This year
Statistics
Stories by
fatihturker
Show HN: Efficient LLM Architectures for 32GB RAM (Ternary and Sparse Inference)
2 points
fatihturker
2026-03-09T20:30:18Z
github.com
Show HN: Run 500B+ Parameter LLMs Locally on a Mac Mini
17 points
fatihturker
2026-03-09T06:47:40Z
github.com
Could ternary weights make 500B models runnable on consumer hardware?
7 points
fatihturker
2026-03-08T20:38:32Z
opengraviton.github.io
Show HN: OpenGraviton – Run 500B+ parameter models on a consumer Mac Mini
13 points
fatihturker
2026-03-07T16:37:03Z
opengraviton.github.io