PinnedEdward Tsang·Jul 18, 2025Local RAG Chatbot with Ollama on MacLightweight, private, and customizable retrieval-augmented chatbot running entirely on your Mac.
PinnedEdward Tsang·Nov 23, 2025How and why to run Ollama on your own Mac?The reason is simple: because you can. M1 or later Macs with 16GB of RAM or more are powerful enough to run useful models on device without…A response icon2A response icon2
PinnedEdward Tsang·Jun 23, 20195 minutes to Install Imagemagick with HEIC support on Ubuntu 20.04 (and 18.04) DigitalOcean5 mins guide. How to setup Imagemagick with HEIC/HEIF support on Ubuntu 20.04. I am writing this because the default…A response icon15A response icon15
PinnedEdward Tsang·Dec 11, 20185 minutes to Install Hyperledger Fabric v2.x (and 1.x LTS) on Ubuntu 20.04 DigitalOceanYes, It can be done, in 5 mins or so. So I won’t waste too much time to explain these to you. Just get a basic Ubuntu 20.04 Droplet from…A response icon3A response icon3
Edward Tsang·Jun 12I ported a research KV-cache quantizer KVarN to Apple Silicon from my iPhone in Japan, using a $30…I just shipped mlx-kvarn: the first MLX-native implementation of KVarN, a KV-cache quantization method from a 2026 Huawei paper. It gives…
Edward Tsang·May 11Why Coding Is the Perfect Job for AI Agents (And Why That’s Good News for Most Developers)A two-part essay on the deep reasons coding is uniquely suited to AI agents, and why developers shouldn’t expect their compensation to…
Edward Tsang·May 6Coding from Anywhere with Claude Code and Qwen Code: My macOS Tahoe Setup with mosh, tmux, and…If you live in Claude Code or Qwen Code and want to keep coding from your iPhone or iPad without sessions dying every time the train goes…A response icon1A response icon1
Edward Tsang·Apr 21TurboQuant Doesn’t Work on Qwen 3.5 — So I Made It WorkA month ago, Google published a blog post about a paper called TurboQuant. Memory chip stocks lost billions in market cap within hours. The…
Edward Tsang·Apr 18Why Pay Full Price? 10 Chinese Coding Agents Offering Pennies-Per-Token AIWhile the Western AI coding market gets all the attention, China has quietly built a parallel ecosystem of coding agents that rival — and…
Edward Tsang·Feb 5How to Securely Access Ollama and Swama Remotely on macOS with CaddyAccess your local AI servers from anywhere with separate authentication for each backend