Apple Silicon Python Packages

mlx-audio

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

mlx-vlm

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

veloxquant-mlx

Fast KV-cache quantization for Apple Silicon (MLX) — 43 research-adapted compression methods with Metal kernels

mflux

Apple MLX native implementations of state-of-the-art generative image & video models

laya-mlx

Native MLX runtime for Laya typed decision models — 7–14 ms short decisions on M3 Max. No text generation, PyTorch, or cloud API.

metal-linalg

QR, symmetric eigendecomposition and SVD for batches of matrices on Apple Silicon GPUs, for MLX and PyTorch. 2x to 10x gain in performance. 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.

rapid-mlx

Rapid-MLX is an open-source (Apache 2.0) OpenAI- and Anthropic-compatible LLM inference server for Apple Silicon, built on MLX, focused on reliable tool calling for coding agents. Up to 4× faster than Apple's MLX (mlx-lm) on the same weights.

brain-mcp

The recorder for your AI conversations — local-first MCP memory that keeps byte-exact copies of your Claude Code, Codex and Pi sessions (Claude Code deletes its own after 30 days) and answers with a citation or abstains. DuckDB.

mlx-kquant

Native K-quant support for MLX, with a quantization and fine-tuning toolchain for Apple Silicon

lucid-dl

Lumerico's Comprehensive Interface for Deep Learning

mtplx

The fastest way to run Qwen 3.8 Flash Next, Qwen 3.8 27B and Ternary Bonsai 2 27B on a Mac: 125 tok/s in OpenCode on an M5 Max, and a 27B model on 16 GB Macs. Native MTP speculative decoding on Apple Silicon, exact at any temperature. OpenAI and Anthropic compatible local server.

demucs-mlx

Split any song into stems — vocals, drums, bass, and more. Fast music source separation for Apple Silicon, powered by MLX.

mlx-audio-io

Native audio I/O for MLX on macOS and Linux

gmlx

Local inference platform for K/IQ-quant GGUF models on Apple Silicon

mlx-spectro

High-performance STFT/iSTFT for Apple MLX with fused Metal kernels and autograd support

ax-engine

One Mac process. Many models. Real speed. Multi-model LLM serving with prefix reuse, MTP acceleration, and OpenAI APIs — built for Apple Silicon, measured against mlx-lm and llama.cpp.

vllm-mlx

High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.

system1

Not an LLM. Teach bounded decision skills from examples or observed APIs, validate, then run and save them locally. Optional MLX acceleration.

mlx-audio-separator

MLX-native audio stem separation for Apple Silicon (Demucs, MDX, MDXC, VR, Roformer).

opendecider

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVIDIA, Apple Silicon, LM Studio, Ollama and vLLM.

jaketts

Local, offline text-to-speech for macOS using Kokoro-82M — GUI + CLI, 54 voices, no cloud API.

jax-mps

A JAX backend for Apple Metal Performance Shaders (MPS), enabling GPU-accelerated JAX computations on Apple Silicon.

mlx-dspark

Up to 4× faster LLM decoding on Apple Silicon, lossless. Native MLX port of DeepSeek's DSpark & z-lab's DFlash speculative decoding — Gemma-4, Qwen3.8, Muse-Glimmer, Nemotron, LFM2.5, Ornith-1.0, ternary Bonsai-27B.

laya-apple

Correctness-validated heterogeneous Laya runtime for Apple Silicon (MLX GPU + Apple Neural Engine)