AI TCH LIF GO Goh Chun Lin Local LoRA Training for Specialised Domain Data Like any software engineer, I love local control. While cloud APIs limit customisation, local fine-tuning allows us to update model weights…
AI AB Abiral Sthapit Setting up local agentic AI with mlx-lm on mac os Install Python version 3.11 through brew and create a virtual environment for mlx. Creating a virtual environment isolates your project…
SPT AI AU AutomatosX We Can Run Gemma 4 12B on Apple Silicon Locally (with ax-engine + MLX) I built ax-engine to answer a practical question that a lot of people ask:
AI RA Rajveer Rathod I Built a FlashAttention Kernel That Beat MLX’s SDPA. Then I Discovered It Was Useless. I spent 8 hours writing a Metal compute kernel in MLX. It was numerically correct. It passed 221 tests. It was 1.32× faster than Apple’s…
AI TCH MA Majid The PR You Would Have Opened Yourself: Porting Transformers to MLX with AI In 2026, AI code agents have evolved from simple autocomplete tools into powerful systems capable of one-shotting complex solutions. As…
AI SPT TCH MI Michael Hannecke Run OpenCode with Gemma 4 Locally on Apple Silicon A complete step-by-step guide to setting up a private, zero-cost AI coding agent on your Mac. No API keys, no cloud, no data leaving your…
TCH MDA ECO AI JO Joseph Miguel Zero-shot voice cloning using open source models, Python, and MLX on macOS In the James Bond series ‘Diamonds Are Forever’ (1971), the villain Ernst Stavro Blofeld and his associates employ a sophisticated…
AI JO Joana Levtcheva Agno + MLX + Agent Lightning: Automatic Prompt Optimization for a Job-Search Agent Automatic Prompt Optimization (APO)