Locals: Open-Source Apple Silicon Engine Runs Local LLMs Up to 3x Faster
SumitGup · x · 2026-10-22
@machinestein introduces Locals, an open-source LLM inference engine for Apple Silicon claiming up to 3x faster local inference. It works as a drop-in replacement for Ollama, MLX-LM, or llama.cpp so coding harnesses and autonomous agents can use it immediately. Under the hood is a claimed theoretical breakthrough in complexity theory enabling faster algorithms for DeltaNet architectures, grammar-constrained decoding, tool calling, and structured outputs. Available on GitHub.
More from coding & agent
- Stanford's Librarian Agents: RL-curated workspaces boost long-context QA by 30+ points — khademinori · 2026-10-22
- I built an AI software factory that turns GitHub issues into PRs on autopilot — Pavan_Belagatti · 2026-10-22
- Dev builds a full in-game map editor for his AI-made dungeon crawler with Codex — Dimillian · 2026-10-22
- HKU's PrismaCoder: Open Multimodal Code Models Rival Proprietary Systems — hkunlp · 2026-10-22
- Walmart Opens MCP Agent Gateway While Amazon Locks Out AI Shopping Agents — sanjaykalra · 2026-10-22
- open-duet: open-source self-hosted Claude Duet alternative hits 5.9k GitHub stars — matchaman11 · 2026-10-22