Add it to a GitHub README or profile β the card updates as the ranking changes:
Hit your Claude Code usage limit? Keep going free and offline on a local model: Qwen 3.8, Gemma 4, and Qwen 4 the day it ships. Runs on Apple Silicon Macs (MLX), Linux and Windows (llama.cpp) with no API key. Your code stays home.
Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server, 65 tok/s Qwen 3.5 122B, Llama 3.3 70B, Gemma 4 31B. Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.
Building AI tools and learning as I go: mobile computer vision, medical ML, business automation. Started with a chicken problem, ended up doing neuroscience research. Still figuring it out.
Turn a story into a finished film β on your own Mac, no cloud. Story Forge is a local-only generative cinema pipeline: stills, motion, voices, music, grade, and sound, start to finish. Flux Β· LTX-2 Β· Piper Β· ACE-Step Β· ffmpeg β built for and running 100% on a Mac (M5, 128GB).
Self-hosted family command center for a spare iPad β voice control, OCR document scanning, meal planning, chore tracking, and seasonal themes. No subscriptions, no cloud.
Self-hosted family command center for a spare iPad β voice control, OCR document scanning, meal planning, chore tracking, and seasonal themes. No subscriptions, no cloud.