amos-labs/expertcache

Page-aware Metal inference research for oversized sparse mixture-of-experts models on Apple Silicon

4 best points · 0 comments · 1 Hacker News post · 10 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: ExpertCache – Run the Full GPT-OSS 120B (63GB) on a 16GB M1 Pro (4 points, 0 comments, by rick_barkley, 2026-08-08)