m1

Perf monitoring CLI tool for Apple Silicon

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

Run larger LLMs with longer contexts on Apple Silicon by using differentiated precision for KV cache quantization. KVSplit enables 8-bit keys & 4-bit values, reducing memory by 59% with <1% quality loss. Includes benchmarking, visualization, and one-command setup. Optimized for M1/M2/M3 Macs with Metal support.

Play Overwatch on your Mac. Free and open source, made for Apple Silicon.

IDA loader for Apple's 64 bits iBoot, SecureROM and AVPBooter

VGGT 3D Vision Agent optimized for Apple Silicon with Metal Performance Shaders

A Home Assistant Custom Component for Maestro MCZ (cloud)

Rasa on ARM-based Macs (Native/Docker)

Unofficial native Mixxx builds for macOS (Apple Silicon/Intel) and Linux

Use Rosetta to run amd64 binaries on your M1 with Multipass.

Boilerplate for GPU-Accelerated TensorFlow and PyTorch code on M1 Macbook

Python script to set Recovery Lock key for Apple M1 computers.

🎨 Native AI image generation for Apple Silicon with Qwen-Image. Lightning LoRA acceleration for fast 4–8 step runs. Zero Docker, just works.

Free, open-source game launcher toolkit for Apple Silicon Macs. Set up Battle.net, Steam, Epic and GOG with separate Wine environments, Mac launch shortcuts and documented compatibility.

A port to Apple Silicon (see branch silicon)

The NVIDIA Container Toolkit for Mac — Give any Docker container full Apple Silicon Metal GPU access. 100+ GPU operations, LLM inference, training, image gen, audio, embeddings. Zero CUDA. Just Metal.

Run Tencent's Hunyuan3D 2.1 image-to-3D model without CUDA — natively on Apple Silicon (MPS) and AMD GPUs (ROCm), now with PBR texturing

Python demos for testing out the Stable Diffusion's XL (SDXL 0.9) model.

A python training pipeline for Apple MLX to produce a fine tuned model with Apple Neural Engine Support

Chinese fine-tuned Laya decision model weights (MLX, Apple Silicon) — 中文微调 Laya 决策模型: 消息路由/紧急度/优先级/检索选词, 一次前向全出, ~27ms