Mlx: open-source projects on GitHub
47 repositories on Mlx, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.
// RELATED TOPICS
LOCAL AI VOICE STUDIO WITH CLONING AND DUBBING
Open-source cross-platform tool for voice cloning, video dubbing, and audiobook creation in 646 languages. Runs fully locally without cloud APIs or registration.
★ 110,614 · PythonLLM Server for Apple Silicon
A powerful inference server with support for continuous batching and SSD caching, running on Apple Silicon and controlled via the macOS menu bar.
★ 14,445 · PythonMLX-AUDIO: SPEECH ON APPLE SILICON
mlx-audio — library for TTS, STT and STS on Apple's MLX framework. Runs efficiently on Apple Silicon. 8192 stars on GitHub.
★ 8,267 · PythonSpeech Tools for MLX
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.
★ 7,115 · PythonMLX-Powered Laya Decisions
A native MLX runtime for Laya typed decision models that runs short decisions in 7–14 ms on an M3 Max. It avoids text generation, PyTorch, and cloud APIs.
★ 7,102 · PythonRUN VLM LOCALLY ON MAC
mlx-vlm runs and fine-tunes vision-language models (LLaVA, Florence-2, Idefics) on Apple Silicon via MLX. Everything works locally on your Mac without GPU servers.
★ 5,847 · PythonMLX-VLM: RUN VLM ON MAC
Package for running and fine‑tuning Vision Language Models on Mac via MLX. 4.7K★
★ 4,787 · PythonBONSAI DEMO SHELL TOOL
Mini-demo of the Bonsai project on Shell — shows how to quickly automate tasks using simple scripts.
★ 3,523 · ShellMTPLX SUPERFAST LAUNCH
MTPLX lets you run Qwen 3.8 Flash Next and Qwen 3.8 27B on Mac at 125 tokens/sec in OpenCode. Thanks to MTP speculative decoding on Apple Silicon, results stay accurate a
★ 2,706 · PythonLocal Claude Code
Run Claude Code entirely on-device with Apple Silicon using an MLX-native server compatible with the Anthropic API. Supports local Qwen 3.5 122B, Llama 3.3 70B, and Gemma
★ 2,578 · PythonNATIVE LLM SERVER FOR MAC
LLM server compatible with OpenAI+Anthropic, no Python required. Includes MLX Core macOS: chat, agent, and tool calling.
★ 2,472 · ZigFast Local AI Engine
Rapid-MLX is the fastest local AI engine for Apple Silicon, running 4.2× faster than Ollama and providing a cached first-token time of just 0.08s.
★ 2,185 · PythonLOCAL OPEN-SOURCE AI AGENT
Atomic-Chat is a private AI engine for running LLM locally without internet, fully offline on your computer. ⭐ 967 stars on GitHub.
★ 2,008 · TypeScriptVLLM-METAL: ACCELERATING LLM ON APPLE SILICON
vllm-metal is a community‑maintained plugin that brings Metal‑based acceleration to vLLM on Apple Silicon. It uses MLX to run LLMs on macOS with low latency and high thro
★ 1,997 · PythonNATIVE LLM CHAT FOR MAC ON MLX
Klee is a native macOS app for LLM chat on MLX engine. Runs 100% locally on Apple Silicon without cloud. Written in Swift with ShipSwift framework.
★ 1,774 · SwiftParlor AI on device
Parlor is an open project that enables natural voice and visual dialogues with AI running fully locally on your device. It is built on the Gemma 4 E2B and Kokoro models.
★ 1,752 · HTMLSTARTLUX‑DECISION: AI DECISIONS
Open decision models from 0.8B to 27B give calibrated probability for each option in one pass and a short thought only when unsure. They serve as the available inference
★ 1,745 · PythonLOCAL AI FOR MAC OFFLINE
Nativ runs open LLMs locally on Apple Silicon. No data ever leaves your Mac. Built on MLX and Swift.
★ 1,591 · SwiftOpenMed AI for Healthcare
OpenMed is an open-source Python project using AI for medical data analysis and clinical decision support.
★ 1,365 · Pythonvllm-mlx LLM Server
OpenAI and Anthropic compatible server for Apple Silicon that runs LLMs and vision models with continuous batching and MCP tool calling, achieving 400+ tokens/s.
★ 1,260 · PythonASSETFURNACE: LOCAL IMAGE-TO-3D WITH RIGGING
Open-source pipeline for generating game characters from text or image. Creates textured, rigged, and animated GLB models locally on Apple Silicon or NVIDIA.
★ 1,218 · PythonAI Film Studio on TensorFold
Plan films with crew workflows, generate images with Qwen-Image/FLUX and videos with MiniMax H3 on TensorFold runtime for Mac and NVIDIA DGX Spark.
★ 1,087 · PythonTensorFold AI Film Studio
Plan films with Slate workflow, generate Qwen-Image/FLUX images and MiniMax H3/FastH3 videos with sound on Mac or NVIDIA DGX Spark via TensorFold.
★ 1,055 · PythonSiliconScope — Apple Silicon Monitor
Native Apple Silicon system monitor in SwiftUI without sudo: tracks ANE, Media Engine, and memory bandwidth.
★ 1,024 · SwiftSPARK-X2.6: AGENTS ON DEVICE
Open Spark-x2.5 model series focused on agentic capabilities. Runs locally on device without cloud. 814 stars on GitHub.
★ 911SWIFTLM: SWIFT LLM ON APPLE
Native LLM inference server in Swift with MLX, OpenAI‑compatible API, SSD streaming for MoE >100B and TurboQuant KV‑cache compression.
★ 799 · SwiftMLX-DSPARK: 4X LLM ACCELERATION
Portable MLX port of DeepSeek DSpark and z‑lab DFlash for accelerating LLM decoding on Apple Silicon up to 4× without quality loss.
★ 740 · PythonMLX Studio: Main JANG_Q Tool
Image generation and editing, chat and code in one place with support for OpenClaw and Anthropic API.
★ 727SLOTSTREAM LAUNCHES QWEN3.8 ON MAC
Run Qwen3.8‑Flash‑Next (125B MoE, 104 GB at 4‑bit) on Mac by streaming experts from SSD on demand. Implemented with MLX + Swift, it offers an Ollama‑compatible API.
★ 673 · SwiftLOCAL AI AUDIO GENERATION
audio-studio-mcp runs Stable Audio 3 on Apple Silicon via MLX and on NVIDIA GPU via PyTorch. Generates background music and sound effects for Claude Code and any MCP clie
★ 669 · PythonFABRIC CREATIVE 3D CODING
Fabric is a Node‑based environment for creative coding, 3D graphics and image processing, inspired by Quartz Composer. In Swift it uses Metal for fast rendering and suppo
★ 606 · SwiftRUN ANY AGENT ON ANY MODEL
llmman lets you run any AI‑agent on any model stored as an OCI image. It supports Claude Code, Codex, llama.cpp, MLX and other popular LLM frameworks.
★ 590 · RustVMLX - NEXT-GEN MLX MODELS
Ultra-fast compressed MLX models with two-level cache, hybrid scheduler, and continuous batching.
★ 561 · PythonVLLM ON C++: POWERFUL SOLUTION
vllm.cpp is an open-source C++ engine, fully compatible with vLLM: continuous batching, paged KV-cache, GGUF support, RadixAttention and cache-aware scheduling. 447★, bui
★ 487 · C++Detto: No-Leak Meetings
Detto is a macOS app for recording meetings, dictation, and a local knowledge base without data leaks.
★ 484 · SwiftPMETAL: THE ACCEL LLM ON APPLE SILICON
PMetal — Rust framework for high‑performance LLM inference on Apple Silicon. Supports local inference, LoRA/QLoRA fine‑tuning, serving, quantization, and MLX/Metal accele
★ 333 · RustFLAMA: ONE LINE FOR AI API
Framework for fast deployment of AI models as API with built-in chat and MCP support.
★ 307 · Pythonphi - Simple Phi-4 Launch
Run the powerful multimodal Phi-4 model directly on your Mac with Apple Silicon — no cloud, no complex setup.
★ 280 · Jupyter NotebookBUILD YOUR AI INTRANET
Autonomous grid unites your computers into a single infrastructure for running AI models: training, fine‑tuning and inference. Supports distributed computing, fine‑tuning
★ 278 · PythonLLMKUBE: LLM IN KUBERNETES
LLMKube - Kubernetes operator for LLM inference on heterogeneous GPU fleet: NVIDIA CUDA, AMD Vulkan, Apple Silicon Metal. Supports llama.cpp, vLLm, TGI, mlx-server, multi
★ 266 · GoAlbatross: Open AI Agent
Albatross is an open terminal AI agent with transparent multi‑model routing. It runs locally via Ollama, LM Studio, MLX or in the cloud using your API keys.
★ 244 · RustJANGQ Quantization for Apple Silicon
JANG — adaptive mixed-precision quantization of GGUF models for MLX on Apple Silicon. Requires using the JANG_Q runtime for maximum performance.
★ 233 · PythonCOMPACT TTS WITH VOICE CLONING
Multilingual text-to-speech model with zero-shot voice cloning. Runs locally on GPU, CPU, Apple Silicon, and in browser via WebGPU.
★ 219 · PythonANUBIS: BENCHMARK LLM ON APPLE SILICON
anubis-oss — Swift utility for local LLM launch and benchmarking on Apple Silicon. It measures speed and accuracy of GPU inference, comparing results with CPU baseline an
★ 217 · SwiftTraining GPT for $50
The project shows how to train your own GPT-like model on a $50 budget using accessible cloud resources and open-source code.
★ 45 · PythonLabLLM on macOS
LabLLM is a native macOS app where you can build the architecture of a tiny language model, train its weights, and see the model emerge from scratch on Apple Silicon usin
★ 39 · SwiftSelf-hosted LLM gateway
A single Go binary turns your Mac and Linux machines into a private inference cluster featuring multi‑machine routing, sharding via llama.cpp‑RPC, and support for the Ope
★ 38 · GoNew projects on this topic in Telegram
Telegram →