Reading up on local-ai
5 deep · digging since dec 23, 25
- Unsloth Studio | Hacker News
Unsloth launches Unsloth Studio, an open-source, no-code web UI for locally running, training, and exporting 500+ open models with 2x faster training and 70% less VRAM.
- Ask HN: How are you doing RAG locally?
Hacker News commenters share diverse local RAG setups including vector databases, SQLite FTS5, BM25, and lightweight tools like Chroma, Qdrant, and AnythingLLM.
- Run AI Models Locally: A New Laptop Era Begins - IEEE Spectrum
The push to run AI models locally is driving the biggest change in laptop architecture in decades, with new NPUs, unified memory, and Microsoft's AI Foundry.
Takes
What a great conversation today. It's such an unbelievably exciting time. And Local AI only makes it more so!
@dhh
This is a glimpse of big changes ahead of us. If you’re betting on big central models you should think twice. I run the exact same setup (M5 MacBook, qwen3.6-27B, pi, ollama) and while its not as fast or good as one of the big central models, it’s past the line of “cool demo” into “truly useful.” Kind of where the big frontier models were in late 2025. In ~24 months we might have local models that are fast and good enough for most tasks.
@rsms