Skip to content
MONOGRAPH

Explore

Guides on self-hosting LLMs, GPUs for LLM inference and local RAG. Every listing here is an example: working titles, no prices, nothing for sale yet.

3 publications

AI & Technology

Self-hosting open LLMs

Working title. A practical guide to self-hosting LLMs: host your own LLM on hardware you control, using open weight models.

Price TBAAuthor TBAExample, not for sale

Cloud & Infrastructure

GPU sizing for inference

Working title. How to size GPUs for LLM inference: estimate how much VRAM a model needs before you buy or rent.

Price TBAAuthor TBAExample, not for sale

AI & Technology

Private RAG on your own stack

Working title. Building local RAG: a private, self-hosted RAG pipeline where documents never leave your infrastructure.

Price TBAAuthor TBAExample, not for sale