How to Setup a Local Coding Agent on macOSVisit link →Running Gemma 4 26B-A4B and Qwen3.6 35B-A3B locally with llama.cpp, MTP speculative decoding, multimodal support, and PI as a coding agent.June 16, 2026ai macos performancePermalink: 2026/w25/how-to-setup-a-local-coding-agent-on-macos Copy Related LinksI ran 120B MoE models on my M1 Max ai macos performanceGitHub - lithos-ai/lithos-metal ai macos performanceOllama is now powered by MLX on Apple Silicon in preview ยท Ollama Blog ai macos performanceGitHub - davide-troiani/moeshift ai macosScrawl: show an agent the problem ai macos← Back to Week 25
2026/w25/how-to-setup-a-local-coding-agent-on-macos