1.
2.
DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
(news.ycombinator.com)
3.
Running Gemma 4 locally with LM Studio's new headless CLI and Claude Code
(news.ycombinator.com)
4.
5.
Flash-MoE: Running a 397B Parameter Model on a Laptop
(news.ycombinator.com)