I ran 120B MoE models on my M1 MaxVisit link →I've been trying to run large language models on my MacBook Pro. It has an M1 Max and 32GB of RAM, so a 60GB model obviously won't fit entirely in memory.November 13, 2026ai macos performancePermalink: 2026/w46/i-ran-120b-moe-models-on-my-m1-max Copy Related LinksGitHub - lithos-ai/lithos-metal ai macos performanceHow to Setup a Local Coding Agent on macOS 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 46
2026/w46/i-ran-120b-moe-models-on-my-m1-max