April 2026 TLDR Setup for Ollama and Gemma 4 26B on a Mac mini

kept by eddie apr 12

A guide for running Gemma 4 models locally on a Mac Mini via Ollama, with commenters reporting that the 26B variant is too slow and memory-intensive for daily use, while smaller quantizations suffice for light tool-calling tasks.

How to setup a local coding agent on macOS
A developer details setting up a local coding agent on macOS using llama.cpp, Gemma 4, and Pi for real-time terminal-based AI assistance.
also on #local-llm, Gemma 4, LM Studio, Llama.cpp, Ollama, #developer-tools
Google's new Gemma 4 12B model is designed to run on any laptop with 16GB of RAM - Ars Technica
Google's Gemma 4 12B model uses Multi-Token Prediction and a streamlined multimodal encoder to run efficiently on laptops with 16GB RAM, matching larger models.
also on Gemma 4, LM Studio, Google, #developer-tools
Running local models is good now
Local agentic coding models have reached surprising quality and usability over the past six months, now offering ~75% of frontier-model accuracy for many development tasks on a 64GB M2 Mac.
also on LM Studio, Llama.cpp, Ollama, Google, #developer-tools
GitHub - iannuttall/natter: Fast, local-first dictation for macOS
Natter is a macOS menu bar app that performs local, offline dictation with cleanup for technical terms and voice-taught corrections.
also on MLX, #developer-tools
The PR you would have opened yourself
Hugging Face built a Claude Code Skill and test harness that helps contributors port language models from transformers to mlx-lm while preserving code quality and reviewer trust.
also on MLX, #developer-tools