R_REDDYX.XYZ

Metal: open-source projects on GitHub

32 repositories on Metal, picked by the REDDYX AI agent. Each has a summary, key features and a breakdown. Sorted by stars.

// RELATED TOPICS

LLM 2094Apple Silicon 56Mlx 47Gguf 47Llama Cpp 56Inference 95Ios 90LLM Inference 76Local AI 82On Device AI 38Swift 113Cuda 48GPU 48Local LLM 107
ly05010419/MacNativeGames

Native Zelda on Apple Silicon

Runs Breath of the Wild and Tears of the Kingdom natively on Apple Silicon by translating NVN API calls to Metal. Requires own game files.

★ 7,811 · C
drumih/turbo-fieldfare

TURBO-FIELDFARE - GEMMA 4 ON MACBOOK

Run Gemma 4 26B‑A4B on any MacBook with an M‑series chip using under 2 GB of RAM. Fast and with no extra resources.

★ 7,391 · Swift
jhaizhou-ops/S2Arm

Native Switch Games on Apple

Rewrites Switch game code to ARM64 and renders via Metal, letting you play your own Switch library natively on iPhone, iPad, and Mac.

★ 2,981 · C#
youssofal/MTPLX

MTPLX 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 · Python
incoai/splash

Local AI Engine

Splash lets you run machine learning models directly on Apple‑silicon Macs, using the full power of CPU and GPU without relying on the cloud.

★ 2,284 · Python
withcatai/node-llama-cpp

RUN LLM LOCALLY IN NODE.JS

Run AI models directly on your computer via Node.js. Enforced JSON schema validation right at the generation level.

★ 2,205 · TypeScript
vllm-project/vllm-metal

VLLM-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 · Python
trymirai/uzu

UZU: Powerful Engine for AI Models

High-performance inference engine for AI models in Rust. Fast, reliable, efficient.

★ 1,586 · Rust
RunanywhereAI/wally

VOICE ASSISTANT FOR MAC

Wally lets you control Mac by voice and search local documents offline without internet. It runs on Apple Silicon M1 using an on-device offline LLM via llama.cpp and RAG

★ 1,571 · C++
voyager-so/vork

Headless 3D Engine for AI Agents

A Rust-based headless 3D and VFX engine designed for AI agents to simulate, render, and interact with virtual environments without a GUI.

★ 1,565 · Rust
RunanywhereAI/RCLI

RCLI — Voice AI

Voice AI with RAG, no cloud: chat with Mac and request documents locally.

★ 1,507 · C++
tenstorrent/tt-metal

tt-metal - Metallic Operations Library

TT-NN operator library and low-level programming model for TT-Metalium kernels to accelerate AI workloads on proprietary hardware.

★ 1,505 · C++
chrishayuk/larql

RUST RUNTIME FOR LLM INFERENCE AND EDITING

larql — Rust runtime to run, serve, and edit models. VINDEX3 format makes models executable and inspectable. 1173⭐ on GitHub.

★ 1,175 · Rust
wici-ai/inferssd

RUN MODELS LARGER THAN VRAM

inferssd runs MoE models exceeding RAM and VRAM by streaming experts from SSD. Built on llama.cpp with GGUF, CUDA and Apple Silicon support. 288 stars on GitHub.

★ 1,108 · C++
christopherkarani/Wax

WAX: SINGLE-FILE AI MEMORY

Wax is a single‑file memory for AI agents with sub‑millisecond RAG on Apple Silicon, written entirely in Swift and optimized for Metal.

★ 810 · Swift
SharpAI/SwiftLM

SWIFTLM: 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 · Swift
ARahim3/mlx-dspark

MLX-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 · Python
zhongkaifu/TensorSharp

TENSORSHARP - POWERFUL .NET LLM

A library for quickly launching GGUF models on .NET with GPU support, console app, web chat, and an API compatible with Ollama and OpenAI.

★ 679 · C#
Fabric-Project/Fabric

FABRIC 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 · Swift
hybridgroup/yzma

YZMA: Local LLM in Go

Integration of llama.cpp into Go applications for local inference with hardware acceleration. 496 stars on GitHub.

★ 496 · Go
d2r-mobile/d2r-mobile

DIABLO II ON IPHONE AND ANDROID

Port of Diablo II: Resurrected for iOS, macOS, and Android. Offline play, touch controls, one-tap Runewords, 100 Greater Rift levels. Metal on Apple, Vulkan on Android. R

★ 406 · C
zeraix/zeraix

ZERAIX: LOCAL AI DESKTOP

Local open-source environment for running AI models on device. Speeds up inference without cloud.

★ 405 · TypeScript
Epistates/pmetal

PMETAL: 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 · Rust
robzilla1738/harness-terminal

GPU TERMINAL FOR CODING

Native macOS terminal with GPU rendering, persistent sessions, and coding-agent workflow support. Enables SSH connections, runs as a daemon and CLI tool on Linux, and opt

★ 309 · Swift
raketenkater/ggrun

Not a Llama, no stance

Auto-tuned launcher for GGUF models on llama.cpp — server with multi‑GPU support, hardware‑specific tuning, and crash recovery. Stars: 226.

★ 284 · Go
JosefAlbers/phi

phi - 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 Notebook
defilantech/LLMKube

LLMKUBE: 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 · Go
engeldlgado/toshllm

TOSHLLM: RUN LLM ON MAC

TOSHLLM — a native macOS app in Swift that runs large language models locally on Intel‑Mac with AMD GPU, using Metal acceleration. Supports llama.cpp and is compatible wi

★ 258 · Swift
tgo-app-dev/vpipe

REAL-TIME MULTIMODAL AI PIPELINES ON APPLE SILICON

vpipe runs LLMs and image generation in real time on Apple Silicon. Uses ANE and Metal for maximum performance without GPU.

★ 257 · C++
timtoole02/Camelid

CAMELID: LOCAL AI ON RUST

Camelid — a Rust‑native backend for local inference, compatible with models via evidence‑gated compatibility. Supports Apple Silicon, GGUF, Llama and other LLMs, runs ful

★ 221 · Rust
Awis13/liberty-pro-max

GTA IV Native on Apple Silicon

Statically recompiled GTA IV 1.0.8.0 for Mac with Metal renderer, TAA, and 100+ fixes. Build from your own game files.

★ 160 · C++
krispuckett/SwiftUIShaders

SwiftUI shaders for UI

Library of 41 ready-made Metal effects for SwiftUI: holographic foil, kaleidoscope, magnetic fields, glitch, neon edges, etc. Integrates via typed View modifiers with ful

★ 105 · Metal

New projects on this topic in Telegram

Telegram →
Metal — 32 open-source GitHub projects | REDDYX AI