AI
AI products, models and agents, and how they are changing work.
Models & ResearchExplainer
How Much RAM and VRAM You Need to Run a Local LLM
Work out the RAM and VRAM a local LLM needs from file size, quantization and context length, with worked examples for 4B, 8B and 30B models.
AI for DevelopersHow-to
Using the Ollama API From Your Own Code
AI Tools & AssistantsHow-to
How to Run an LLM Locally on Windows
AI Tools & Assistants
Chatbots, assistants and generators, compared and explained.
Models & Research
How LLMs and foundation models work and compare.
AI for Developers
RAG, fine-tuning, AI engineering and coding assistants.
All AI stories
The briefing, without the noise.
The stories that matter in technology, every weekday morning.
Free. Unsubscribe in one click.