LOCAL AI

7 min read

A Show HN PDF form demo points at a bigger architecture shift: keep sensitive documents local, expose narrow browser tools to the model, and make AI assistance inspectable.

9 min read

DeepSeek's R1 and V3 models deliver frontier-level performance under an MIT license. Here's how to use them through the API, run them locally with Ollama, and decide when they beat closed-source alternatives.

10 min read

Meta's Llama 4 family brings mixture-of-experts to open source with Scout and Maverick. Here's how to run them locally, access them through APIs, and decide when they beat the competition.

7 min read

NVIDIA's Nemotron Nano 9B V2 delivers something rare: a small language model that doesn't trade capability for speed. This 9B parameter model outperforms Qwen 3B across instruction following, math,...

9 min read

Microsoft's PHI-4 is an MIT-licensed 14 billion parameter model that matches Llama 3.3 70B and Qwen 2.5 72B on key benchmarks. Here is what makes it special, how to run it locally, and why small language models are increasingly practical for real development work.