| |||||||||||| 1 point by | Wondering if anyone has played around with the Strix Halo based systems with 128GB of unified memory for local AI, and what their experience has been so far in running different models:
- Practical limit on number of parameters x quantization
- What you've been using it for
- Which models and inference engines combine well | ||||||||||| Applications are open till July 27. |
source & further reading
news.ycombinator.com — original article
When AI Safety become market capture
Tell HN: Claude Code appends new commit signature even if older settings is off
Novgraph: Persistent Knowledge Graph for Codebases