Similar to This
Previous
GitHub - madhusoodhans/model-cache-cleaner: Claude skill that finds and safely cleans storage used by local AI tools (LM Studio, Ollama, Hugging Face ...
github.com/madhusoodhans/model-cache-cleaner

GitHub - humanrouter/ddtree-mlx: Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive ...
github.com/humanrouter/ddtree-mlx

GitHub - nicedreamzapp/claude-code-local: Run Claude Code with local AI on Apple Silicon. 122B model at 41 tok/s with Google TurboQuant. No cloud, no API fees.
github.com/nicedreamzapp/claude-code-local

Next
