Insights
What Ollama’s move to MLX changes
Speed, memory and model choice on Apple Silicon, and whether it changes what you should run now.
9 minAI
Everything we publish on AI: the models we run on our own machines, what the tools send home, the benchmarks we measure ourselves and the claims we check against the code. Start with the investigations, then the guides.
Guides
OpenClaw runs on a local model. Here is the setup
A private assistant on our test machine, and what it still cannot do.
9 min
Case Studies
How we built our local AI stack
The models, the server and the agents on an M4 Pro, and the constraint that decided each one.
8 min
Guides
OpenCode with a local model, offline
No internet, no API key: the setup, the config and the trade-offs we hit on a Mac.
13 min
Guides
LTX-Video on a Mac delivers, slowly
Hours with the local video model in ComfyUI on Apple Silicon: what consumer hardware gets and where it still falls short.
8 min
Opinion
Per-seat AI pricing eats a small team’s margin
What 5, 10 and 25 seats cost a month at today’s list prices, against one shared Mac.
4 min
Opinion
Three checks before any AI tool touches your stack
Most new tools are a demo, a wrapper or gone by next quarter. The three questions we ask first.
4 min
Opinion
Prove your data never leaves
Most privacy is a promise. With a network monitor, local AI privacy is something you can check.
4 min
Opinion
Open weights is not open source
A model you can download is not a model you are free to use. Two different claims, and what each licence allows.
4 min
Case Studies
A week of coding with no cloud
OpenCode pointed at Ollama with no fallback: what worked, what broke, and what we would do again.
10 min