8 articles
Sora Nguyen runs local models on Apple Silicon for writing and small coding assistants. She has hit the unified-memory wall with both Ollama and MLX, and writes about which stack swap-thrashes first when you open a browser.
Popular categories
Local AI
Open WebUI vs AnythingLLM: A Chat Front End for Ollama or a Document Workspace With RAG Built In
Sora Nguyen
November 19, 2026
Local AI
Ollama vs vLLM for Serving Local Models: One User at a Desk or Many Requests at Once
Sora Nguyen
November 18, 2026
Local AI
llama.cpp vs Ollama on a Home PC: When the Raw Engine Beats the Friendly Wrapper
Sora Nguyen
November 16, 2026
Local AI
Ollama Models Filling Your System Drive: Moving Them to Another Disk Without Downloading Again
Sora Nguyen
November 15, 2026
Artificial Intelligence
Which local model still answers on a 16 GB Mac after the browser has taken half the memory?
Sora Nguyen
October 7, 2026
Local AI
Software Development
A Local Model for Boilerplate vs a Hosted Model for the Hard Diff
Sora Nguyen
September 30, 2026
Local AI
Privacy
Local AI vs Cloud AI: Where Your Prompt Actually Goes, and What the Monthly Bill Really Is
Sora Nguyen
September 27, 2026
Artificial Intelligence
Ollama vs MLX on Apple Silicon: Which Local LLM Stack Hits the Unified Memory Wall First
Sora Nguyen
August 25, 2026