Hatmac Blog
Guides and news on cloud Macs, iOS CI/CD, Xcode builds and running AI models on Apple silicon.
RSS feed
Cloud Mac vs Mac VPS: what's the difference?
A dedicated cloud Mac and a macOS VPS sound similar but behave differently. Here is how they compare on performance, GPU access, Xcode, isolation and cost.
Mac Studio for local LLMs: what fits in 36GB and 96GB
How to work out which local LLMs fit a Mac Studio with 36GB or 96GB: weight and KV cache maths, model classes, the GPU memory limit, and MLX vs llama.cpp vs Ollama.
Mac mini vs Mac Studio as a server
A workload-by-workload comparison of Mac mini and Mac Studio as servers: CI, iOS builds, LLM inference, video and remote desktop, with real monthly costs.
Run Ollama on a Mac mini server
Install Ollama on a Mac mini, pick a model that fits 16GB or 24GB, run it as a service, expose the OpenAI-compatible API and keep it secure.
Best Mac mini hosting providers: how to choose
There is no single best Mac mini hosting provider. Here are the criteria that matter, how common provider types compare, and a checklist you can use.
How to set up a Mac mini cluster
A practical guide to Mac mini cluster setup: node roles, repeatable provisioning with Brewfiles and Ansible, SSH keys, runner labels, monitoring and staged updates.