Liquid AI reveals 8B-A1B MoE trained on 38T
(news.ycombinator.com)
1.
2.
4.
TurboQuant KV Compression and SSD Expert Streaming for M5 Pro and IOS
(news.ycombinator.com)
5.
6.
Running local models on Macs gets faster with Ollama's MLX support
(arstechnica.com)
7.
Ollama is now powered by MLX on Apple Silicon in preview
(news.ycombinator.com)
8.
My 2.5 year old laptop can write Space Invaders in JavaScript now (GLM-4.5 Air)
(news.ycombinator.com)