mlx
Tracked open-source repos tagged mlx, sorted by stars.
Related topics
Topics that frequently appear alongside mlx on the same repo.
Recent risers
Repos created in the last 90 days, tagged mlx.
- #1
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.
★ 640 - #2
Run Qwen3.8-Flash-Next (125B MoE, 104 GB at 4-bit) on Macs with a fraction of that RAM by streaming experts from SSD. MLX + Swift, Ollama-compatible API.
★ 287
- #1★ 52,177+379Star change over the last 7 days
- #2★ 34,759+265Star change over the last 7 days
- #3★ 28,278+63Star change over the last 7 days
- #4
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
★ 21,333+380Star change over the last 7 days - #5
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
★ 14,835+2,880Star change over the last 7 days - #6
Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)
★ 9,587+4Star change over the last 7 days - #7
Examples in the MLX framework
★ 8,925+10Star change over the last 7 days - #8
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.
★ 7,826+23Star change over the last 7 days - #9
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.
★ 7,760+26Star change over the last 7 days - #10★ 6,876+44Star change over the last 7 days
- #11
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
★ 5,462+25Star change over the last 7 days - #12
Local-first healthcare AI: clinical NER & HIPAA PII de-identification that runs 100% on-device. 2,200+ medical models, 21 languages, Apple MLX + Python, no cloud, no patient data leaving your network. Apache-2.0
★ 5,199+20Star change over the last 7 days - #13
The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.
★ 5,185+3Star change over the last 7 days - #14
The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
★ 3,647+81Star change over the last 7 days - #15
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.
★ 3,255+12Star change over the last 7 days - #16
Examples using MLX Swift
★ 2,661+6Star change over the last 7 days - #17
Apple MLX native implementations of state-of-the-art generative image & video models
★ 2,303+8Star change over the last 7 days - #18
Bonsai Demo
★ 2,271+15Star change over the last 7 days - #19★ 2,048+7Star change over the last 7 days
- #20★ 2,012+4Star change over the last 7 days
- #21
3x faster speeds on MLX | Qwen 3.8 27B | Native MTP Speculative Decoding On Apple Silicon With No External Drafter.
★ 1,944+173Star change over the last 7 days - #22
Magenta RealTime 2: An Open-Weights Live Music Model
★ 1,775+33Star change over the last 7 days - #23
A native macOS AI chat app powered by MLX. 100% local inference on Apple Silicon, no cloud required. Built with ShipSwift.
★ 1,761-1Star change over the last 7 days - #24
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.
★ 1,557+6Star change over the last 7 days - #25
This repository provides the code and model checkpoints for AIMv1 and AIMv2 research projects.
★ 1,424+0Star change over the last 7 days - #26
Local AI app and inference engine for agents. Run open-weight LLMs locally — private, 100% offline on your computer. Join our Discord: https://discord.com/invite/8wGSsvmg4V
★ 1,413+20Star change over the last 7 days - #27
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
★ 1,398+8Star change over the last 7 days - #28
LM Studio Apple MLX engine
★ 1,174+2Star change over the last 7 days - #29
AI speech toolkit for Apple Silicon — ASR, TTS, speech-to-speech, VAD, and diarization powered by MLX and CoreML
★ 1,161+4Star change over the last 7 days - #30
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Includes MLX Core macOS app with chat, agent mode, and tool calling.
★ 1,115+245Star change over the last 7 days
