Run and benchmark local AI on Apple Silicon.
What it does
Runs local Ollama chat sessions, benchmarks, and diagnostics on Apple Silicon.
When to use it
Use when operating local models on macOS, running Ollama chat sessions, or measuring model speed and latency.
How to use it
Give it the localLLM project and an operational request; it sets up Ollama, launches chat, or runs benchmarks and diagnostics.
What you provide
- An existing project
Uses
Latest review
What you need · 3
The documented workflow is for macOS.
The documented toolchain targets Apple Silicon.
Access · 3
This skill
http://localhost:11434/api/version
Read
Checks the local Ollama service
ollama
Execute
Installs and starts Ollama
Write
Adds a local mistral model