Havuz

Run models larger than your RAM or VRAM by streaming MoE experts from SSD. Built on llama.cpp.

Speech synthesis, speech recognition and voice activity detection for voice conversation, in C++ on ggml: Qwen3-TTS, Irodori-TTS, Qwen3-ASR,

Source code of Local Code, a private AI agent for Mac, iPad and iPhone. Runs DeepSeek 4.1 on device, with Python, Node.js and a shell built

Slotstream, büyük bir MoE modelini SSD’den parça parça yükleyip yoğun kullanılan expert’leri bellekte önbelleğe alarak Apple Silicon Mac’lerde çalıştıran yerel bir inference engine’dir.

Neden yükseliyor · README, 48 GB M5 Pro üzerinde belirli koşullarda 15.86 tok/s ölçümü ve prompt işleme iyileştirmeleri yayımlıyor; son 28 günde 271 commit ve 5 farklı yazar da yoğun geliştirme faaliyetine işaret ediyor. Ancak proje yalnızca 30 günlük ve mevcut sürüm için nitelikli tam yanıt hızı ölçümünün hâlâ beklediği belirtiliyor.

TurboFieldfare, Gemma 4 26B-A4B modelini Apple Silicon Mac’lerde Swift ve Metal tabanlı özel bir runtime ile yerel olarak çalıştırır.

Neden yükseliyor · 72 günde 6828 yıldız alması ve 8 GB RAM’li Mac’te büyük bir model çalıştırma iddiası dikkat çekiyor. README belirli cihazlarda ölçülmüş decode hızları ve deney kayıtları sunuyor; ancak yıldızlar benimseme veya kalite kanıtı değil. Son 28 günde 4 commit ve 1 farklı yazar olması, geliştirme etkinliği ve ekip genişliği açısından sınırlı kanıt sağlıyor.

A native .NET LLM inference engine and agent runtime for GGUF models. TensorSharp provides a console application, a web-based chatbot interf

Real-time multimodal AI pipelines on Apple Silicon

Sequence Studio: a free, open-source video editor for Mac and Windows

Run large language models locally on Intel Macs with AMD GPUs - native macOS app with Metal acceleration

⚡ Native MLX Swift LLM inference server for Apple Silicon. OpenAI-compatible API, SSD streaming for 100B+ MoE models, TurboQuant KV cache co

Experimental macOS Apple Silicon first recompiler of PS4 programs

Native macOS app for local AI image generation and editing on Apple silicon: Z-Image Turbo, Qwen-Image-2.1, Krea 2 Turbo, Anima Turbo and MO

The local AI app built for the Mac. Run LLMs like Qwen, Gemma and GPT-OSS on Apple Silicon, including models far bigger than your Mac's memo

React ve WebGPU ile animasyonlu liquid-glass orb efektleri oluşturup düzenleyen, sonucu Web veya SwiftUI/Metal kodu olarak dışa aktaran bir editör.

Neden yükseliyor · 44 günlük bir repoda 715 yıldız, gerçek zamanlı görsel düzenleme ile Web ve SwiftUI/Metal dışa aktarımının birleşimine ilgi olduğunu düşündürüyor. Ancak son 28 günde yalnızca 1 commit ve 1 farklı yazar var; yıldızlar dışında benimsenme veya sürdürülebilir bakım kanıtı sınırlı.

Local AI engine in Rust: run GGUF and ONNX models for chat, vision, speech and embeddings on your own GPU, RAM and CPU, with automatic place

Lightning-fast, free, local first voice dictation for macOS with on-device transcription

Most accurate, simple and customisable Apple Intelligence–style glow for SwiftUI, backed by Metal shaders.

Flash weight streaming for MLX: run massive models larger than your RAM on Apple Silicon.

CLI-native local AI image and video generation for people, scripts, and agents — CUDA on Linux, Metal on macOS, plus desktop, web, iPhone, R

Apple Silicon mlx with Zero Dependency Java

Local inference platform for K/IQ-quant GGUF models on Apple Silicon

Fast KV-cache quantization for Apple Silicon (MLX) — 43 research-adapted compression methods with Metal kernels

A native macOS terminal built in Swift, with Metal rendering, CJK input, and a dependency-free terminal core.

Local web UI for h3.c — native Metal video/audio generation with MiniMax-H3 on Apple Silicon, no PyTorch or MLX required.

DeepSeek-V4.1-Flash-1017 on one 256 GB M5 Ultra: 1M context, 70.7-104.9 tok/s decode with DSpark drafts, 1,739-1,867 tok/s cold prompts (8k-

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

Camelid: a Rust-native local inference backend with evidence-gated model compatibility.

Native TypeScript game engine — compiles to Metal, DirectX 12, Vulkan, and OpenGL

TurboQuant KV cache compression for MLX with fused Metal kernels. 4.6x compression at 98% FP16 speed.

Get more intelligence from every bit. Better quantization formats and smarter calibration let larger, stronger models run smoothly on the ha

macOS app for inspecting the layer hierarchy of iOS apps

ML model ports (ASR · TTS · LLM · VLM · vision · audio codecs) on the rlx multi-backend compiler + runtime — CPU/Metal/MLX/CUDA/wgpu

A first-launch intro for SwiftUI apps, made with Liquid Glass and Metal.

AI watermark removal built for Apple Silicon. SynthID-class pixel regeneration, visible vendor labels and provenance metadata, with every pi

The Kimi K3 and DeepSeek-V4-Flash-0731 architectures, reimplemented from scratch in pure Rust (zero dependencies) and verified 1:1 against t

Run a coding model at 300+ tok/s on your Mac. Native Rust + Metal inference engine for LiquidAI LFM2.5-24B-A2B (MLX 4-bit) on Apple Silicon.

Model Dispatch and Memory Allocator: an LLM inference engine for the hardware you own. Custom CPU, ROCm, Vulkan, CUDA, Metal and Level Zero

The Siri drop from iOS 27, for SwiftUI: Liquid Glass that pours out of the Dynamic Island and lights up with your voice. One modifier: .siri

Catch local LLMs spilling into the CPU. One run shows GPU placement, prefill, decode, memory, power and a verdict.

Native Rust, single-binary MLX inference server for Apple Silicon. OpenAI/Anthropic-compatible LLM serving — text, vision, audio, embeddings

Open-source native macOS terminal, up to 4× faster than Ghostty, with workspaces, notifications when Claude Code and other agents need you,

NUEM, uyumlu MacBook’larda kapağın hareketine göre eşzamanlanan, özelleştirilebilir bir katlanma animasyonu sunan macOS menu bar uygulamasıdır.

Neden yükseliyor · Repo yalnızca 12 günlük ve 54 yıldızı var; bu erken ilgi gösteriyor, ancak neden yükseldiğini veya kullanımını doğrulayacak bağımsız kanıt sunulmuyor. Son 28 günde 5 commit’in tek yazardan gelmesi de etkinliğin henüz dar bir ekip tabanına sahip olduğunu gösteriyor.

Native macOS terminal with GPU rendering, durable sessions, coding-agent workflows, and SSH connectivity. Session host, daemon, and CLI supp

The open-source alternative to Minecraft: Java Edition, a complete block-survival game in about 45,000 lines of Swift + Metal. Zero dependen

DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook

GlowEffectKit is a SwiftUI SDK for adding animated glow effect to iOS and macOS components, powered by a bundled Metal shader. More compact

The agentic node editor for live visual effects

A practical lab for exploring Apple's Core AI framework, model assets, specialization, and on-device inference.

Production-grade React Native ink engine with native Skia/Metal drawing and continuous canvas primitives.