Swiftlet, a 10,000-line Swift and Metal project under Apache 2.0, runs Alibaba's Qwen3-Next-80B-A3B at 4-bit in 4.3GB of peak RAM on a Mac, decoding at 4.5–5 tokens per second on an M5, and runs the Q…
Developer ansnadeem released mlxsh, a lightweight command-line tool that serves multiple local MLX models on Apple silicon at OpenAI-compatible endpoints, supporting text-only and multimodal modes, an…
A developer released TurboQuant, a pip-installable adapter for mlx-lm on Apple Silicon that uses a randomized Hadamard transform for data-oblivious, calibration-free quantization of weights and KV cac…
A new open-source tool called mlx-chronos provides a standardized benchmark suite and community leaderboard for comparing local LLM inference engines on Apple Silicon Macs. The tool runs reproducible …
Mlx-Code, a new coding agent, natively integrates Git as its core state machine, enabling developers to branch, diff, and resume from any checkpoint. By mapping the reasoning loop onto Git mechanisms,…
The article describes a technical setup for running a local AI coding assistant (Aider) on Apple Silicon Macs using a custom Python server with the MLX library for direct RAM loading of language model…