#mlx

QR, symmetric eigendecomposition and SVD for batches of matrices on Apple Silicon GPUs, for MLX and PyTorch. Metal kernels per regime, routed to the GPU or the CPU by policies measured per Mac. C++, Python (pip: metal-linalg, metal-linalg-torch), Swift and C.

Model-agnostic generative vision for Python and AbstractCore — text/image/video generation via MLX-Gen, Diffusers, stable-diffusion.cpp, and OpenAI-compatible APIs.

Codam's own fixed, functioning and open source alternative of the miniLibX. MLX42 is a simple cross-platform graphics library running on GLFW and OpenGL.

The full-stack open-source agentic ecosystem.

stabbur — the Norwegian storehouse for your models: build a local LLM library, then run, chat and serve it with MCP tools. Source-available, proprietary.

JANG — GGUF for MLX. YOU MUST USE JANG_Q RUNTIME. Adaptive Mixed-Precision Quantization + Runtime for Apple Silicon

ローカルLLM（mlx / mlx-vlm / llama.cpp / router）を OpenAI 互換 API として起動・管理する軽量サーバー

a Rust runtime for local language models

Everyone swears Claude got lazier. Bring receipts.

Python tools for text to speech (TTS), speech to text (STT), and speech to speech (STS) powered by MLX

该仓库未发布描述。

Examples in the MLX framework