mlx

36 projects share this GitHub topic

Lines connect members that are measurably related to each other. Dot size reflects stars.

🧬 Members

voicebox

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

★ 47.4k

llmfit

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

★ 30.9k

omlx

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

★ 18.3k

einops

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

★ 9.6k

mlx-audio

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX…

★ 7.6k

osaurus

Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution,…

★ 7.4k

mlx-lm

Run LLMs with MLX

★ 6.5k

mlx-vlm

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

★ 5.3k

transformerlab-app

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from…

★ 5.2k

openmed

Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 2,200+…

★ 4.7k

Rapid-MLX

The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling.…

★ 3.4k

mflux

MLX native implementations of state-of-the-art generative image models

★ 2.2k

Bonsai-demo

Bonsai Demo

★ 2.1k

parlor

On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely…

★ 1.9k

Klee

A native macOS AI chat app powered by MLX. 100% local inference on Apple Silicon, no cloud required. Built…

★ 1.8k

magenta-realtime

Magenta RealTime 2: An Open-Weights Live Music Model

★ 1.7k

vllm-mlx

OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama,…

★ 1.5k

mlx-tune

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR…

★ 1.4k

Atomic-Chat

Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your…

★ 1.2k

speech-swift

AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and…

★ 1.1k

mlxstudio

MLX Studio - Home of JANG_Q - Image Gen/Edit + Chat/Code All in one - + OpenClaw (Anthropic API)

★ 920

TheWhisper

Optimized Whisper models for streaming and on-device use

★ 892

ChatMLX

🤖✨ChatMLX is a modern, open-source, high-performance chat application for MacOS based on large language…

★ 833

mlx-audio-swift

A modular Swift SDK for audio processing with MLX on Apple Silicon

★ 736

mlx-omni-server

MLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple…

★ 734

f5-tts-mlx

Implementation of F5-TTS in MLX

★ 644

qwen3-tts-apple-silicon

Run Qwen3-TTS text-to-speech locally on Mac (M1/M2/M3/M4). Voice cloning, voice design, custom voices. 100%…

★ 537

Fabric

Node Creative Coding / 3D / Image Processing tool inspired by Quartz Composer

★ 534

mlx-llm

Large Language Models (LLMs) applications and tools running on Apple Silicon in real-time with Apple MLX.

★ 466

mlx-serve

Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX…

★ 380

mlx-openai-server

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using…

★ 355

Vocello

Vocello — a local, private voice studio for Apple Silicon. Write a script, pick or describe a voice, and…

★ 343

PicoMLXServer

The easiest way to run the fastest MLX-based LLMs locally

★ 327

pmetal

PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving,…

★ 306

shadow

Your computer was paying attention the whole time. 14-modality capture. Proactive intelligence. Computer-use…

★ 75 · GitHub ↗

neo-unify

Toy-scale unified multimodal model experiments — encoder-free understanding & generation with…

★ 47 · GitHub ↗

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.