Tag: apple-silicon
-
I Ran an AI Agent Overnight on My Mac — Here's What It Built
What happens when you run an autonomous coding agent like Claude Code overnight on a Mac — the setup, safety rails, which tasks actually work, the cost and energy use, and how much of the output gets thrown away.
-
The Truth About Mac vs. NVIDIA for AI — I Tested Both
Apple Silicon vs NVIDIA GPU for local AI compared honestly with benchmark numbers — tokens per second, prompt processing speed, power draw, and VRAM vs unified memory. Which to buy for LLM inference, fine-tuning, and training.
-
Apple Shortcuts + AI Is the Automation Stack Nobody Talks About
How to combine Apple Shortcuts with Ollama, ChatGPT, and Claude to automate summarization, voice memos, OCR, and daily briefings on Mac and iPhone. Includes the exact JSON body for calling Ollama's local API and a Tailscale setup for cross-device shortcuts.
-
Fine-Tune Your Own AI Model on a MacBook — Yes, Really
Step-by-step LoRA fine-tuning with MLX on a MacBook — preparing a JSONL dataset, mlx_lm.lora flags, training times on M-series chips, evaluating results, and serving the fused model with Ollama.
-
I Let AI Organize 20 Years of Photos and Files on My Mac
How to use on-device AI on macOS to organize decades of photos and files — Apple Photos ML, local LLM batch renaming, Live Text OCR, and semantic file search. All private, all offline.
-
M1, M2, M3, M4, M5: Does It Still Make Sense to Chase a New Mac Every Year?
Analyze whether annual Mac upgrades still make sense in the Apple Silicon era. Explore the diminishing returns from M1 to M5 and discover the optimal.
-
Run Stable Diffusion on Your Mac — No Cloud, No Limits, No Cost
How to run Stable Diffusion and Flux locally on Apple Silicon with Draw Things and ComfyUI. Real generation times per chip, unified memory advantages, LoRAs, and an honest comparison with Midjourney.
-
Stop Paying for Transcription — Your Mac Does It Better, Free
How to run Whisper locally on a Mac with whisper.cpp Core ML acceleration or MacWhisper. Realistic speed and accuracy versus Otter and Rev, multilingual support, and a private meeting-to-summary workflow.
-
Apple MLX Is the Most Underrated AI Framework Right Now
A practical guide to Apple MLX and mlx-lm on Apple Silicon. Why MLX beats llama.cpp for some workloads, the MLX community models on Hugging Face, and LoRA fine-tuning a local LLM on a MacBook in one afternoon.
-
The MacBook Pro Setting That Doubles Your AI Performance
How to raise the macOS GPU memory limit with sudo sysctl iogpu.wired_limit_mb to run bigger local LLMs on a MacBook Pro. Safe values per RAM tier, persistence setup, High Power Mode, and thermal tips.
-
Your Mac Is a Local AI Supercomputer You're Using at 10% Capacity
How to run local LLMs on Apple Silicon with Ollama. Unified memory explained, which model size fits your RAM, realistic tokens per second on M-series Pro, Max, and Ultra chips, plus a 15-minute setup checklist.
