Run Qwen3.8-Flash-Next (125B MoE, 104 GB at 4-bit) on Macs with a fraction of that RAM by streaming experts from SSD.

LLMxRay — Local LLM Observatory.

A personalized reader that selects Hacker News posts matching your interests

Self-hosted voice agent runtime: speech-to-text, an LLM and text-to-speech streaming into each other in one process.