Notes from the fleet
Can open-source AI replace ChatGPT in your company?
Can open-source AI replace ChatGPT in your company? Where open models already match hosted AI, what it takes to switch, and how to test it on your own work.
Running Gemma 4 on your own GPU servers
How to run Gemma 4 on your own GPU servers: real file sizes, hardware fit for the 31B and 26B A4B models, recommended settings and deployment steps.
Getting started with self-hosted LLMs on your own GPU servers
A practical guide to self-hosted LLMs: pick a model, size your GPU server, run inference on your own hardware and give your team an OpenAI-compatible endpoint.
How to manage a GPU fleet for LLM inference
How to manage a GPU fleet for LLM inference: inventory, models, instances, access control and capacity planning across multiple servers.
How to give your team a private ChatGPT
How to give your team a private ChatGPT: run an open model on your own GPU server, add chat and API access, and control who uses what.
How much does it cost to self-host an LLM for 200 employees?
How much does it cost to self-host an LLM for 200 employees? A worked example with GPU rental, hosted API comparison and the arithmetic so you can check it.