MLX

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

The open-source AI voice studio. Clone, dictate, create.

Hundreds of models & providers. One command to find what runs on your hardware.

MLX: An array framework for Apple silicon

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Examples in the MLX framework

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.

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

Run LLMs with MLX

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

Local-first healthcare AI: clinical NER and HIPAA PII de-identification on hardware you control. 2,200+ medical models, 35 model-backed PII languages, and Python, MLX, Android and browser runtimes. Apache-2.0 SDK.

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

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.

Semantic search over videos using Gemini Embedding 2 or Qwen3-VL.

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.

Bonsai Demo

Run Claude Code 100% on-device with local AI on Apple Silicon. MLX-native Anthropic-API server. 6 fighters incl. Muse-Glimmer 30B (now multimodal — reads images, abliterated), Gemma 4 31B, Qwen 3.5 122B (65 tok/s), DeepSeek V4 Flash (1M ctx). Private, offline, airgap-ready. Built for NDA / legal / healthcare workflows.

Examples using MLX Swift

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.