How to troubleshoot local LLM memory pressure on Mac
Check Activity Monitor, record swap, and retry a GGUF with a small explicit context and one llama.cpp slot. A diagnostic checklist with measured command evidence and clear test limits.
Practical library
Local LLM guides that say exactly what was tested
Setup, optimization, privacy, and troubleshooting guides with platform scope, prerequisites, and a maintained test date.
How to benchmark a local LLM on Mac with llama-bench
Run a repeatable GGUF speed test on Mac, read prompt-processing and generation results separately, and keep the evidence needed for a fair comparison.
How to run a local LLM on a 24GB Mac with llama.cpp
Start a local GGUF with llama-server, open the browser chat, check a first response, and stop the server. Includes the exact setup tested on one 24GB M5 Mac.
How I chose a local LLM for my 24GB M5 Mac from 29 test records
A 29-row registry of MLX and GGUF trials on one 24 GB M5 Mac ended with a pinned Qwen3.8 GGUF. This is a selection record, not a model leaderboard.