TheWhisper breaks Whisper’s 30s fixed chunk limit by supporting flexible chunk sizes for streaming speech-to-text. It provides optimized CoreML and CUDA engines for Apple Silicon and NVIDIA GPUs.
Zinc is a Zig-written LLM inference engine using Vulkan and Metal for AMD RDNA and Apple Silicon GPUs. It supports GGUF quantized models and exposes an OpenAI-compatible API with streaming.
GhostVM offers macOS virtual machines on Apple Silicon with near-native performance, APFS snapshots, deep host-guest integration, and full CLI automation. Ideal for macOS VM sandboxing.
dflash-mlx implements exact speculative decoding for language models on Apple Silicon using Metal and MLX, reducing forward passes with a block-diffusion draft model and per-layer KV cache rollback.
The ‘battery’ utility uses a Shell script and a precompiled SMC binary to control Apple Silicon Mac charging thresholds at the hardware level, with persistence across reboots.
Mac Mouse Fix intercepts macOS raw mouse input to provide trackpad-like gestures and smooth scrolling on third-party mice without vendor drivers. Here’s how it works under the hood.
MacSift is a lightweight macOS disk cleaner built with SwiftUI and MVVM, emphasizing safety with hard-blocked system paths, SHA-256 selection persistence, and Trash-only deletion. Apple Silicon only.
Orion bypasses CoreML to access Apple’s Neural Engine directly via private frameworks, enabling on-device inference and fine-tuning of small LLMs with 8.5x reduced training overhead.
QwenVoice runs Qwen3-TTS 1.7B offline on Apple Silicon using MLX with XPC isolation and supports voice cloning. It balances 8-bit quality and 4-bit speed models in a native macOS/iOS app.
Mochi Diffusion runs Stable Diffusion and FLUX.2 Klein models locally on Apple Silicon Macs using Core ML, achieving ~150MB memory usage with fast inference, all offline.
vllm-mlx is a Python inference server for Apple Silicon that supports OpenAI and Anthropic APIs, featuring SSD-tiered KV cache for long-context agents and continuous batching for performance.
LTX Video Generator for Mac runs complex AI video generation entirely on Apple Silicon by bridging native SwiftUI with a Python subprocess. It manages large models, audio-video sync, and long tasks locally.
macmon is a Rust CLI tool that monitors Apple Silicon power consumption without root, using private macOS APIs. It offers TUI, JSON, and HTTP server modes, plus Prometheus integration.
