http://www.heyuan110.com/tags/apple-silicon/Recent content in Apple Silicon on Bruce on AI EngineeringHugoenTue, 14 Apr 2026 10:00:00 +0800http://www.heyuan110.com/posts/ai/2026-04-14-mac-apple-silicon-ai-workstation/Tue, 14 Apr 2026 10:00:00 +0800http://www.heyuan110.com/posts/ai/2026-04-14-mac-apple-silicon-ai-workstation/<p><img src="http://www.heyuan110.com/posts/ai/2026-04-14-mac-apple-silicon-ai-workstation/cover.webp" alt="Apple Silicon AI workstation comparison: M4 Pro vs M3 Max running Ollama, MLX, ComfyUI, and Draw Things locally" loading="lazy" decoding="async" fetchpriority="low" width="1200" height="630" /> </p> <p>I&rsquo;ve spent the last six months running <strong>Apple Silicon as my primary local AI workstation</strong> — Ollama, MLX, ComfyUI, Draw Things, llama.cpp, all day every day, across an M4 Pro Mac mini (48GB), an M3 Max MacBook Pro (64GB), and a friend&rsquo;s M3 Max Mac Studio (128GB). The conclusion is not what the Apple keynotes would suggest.</p>