Havuz

Headless 3D and VFX engine for agents. Research preview.

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

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.

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.

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

Local speech-to-text at GPU speed: Parakeet, GigaAM and Whisper in pure Rust, as a library and an ollama-like CLI

Native Apple Silicon inference engine for many AI agents at once: C++/Metal, agent-contexts API, 8-bit paged KV, SSD tier (Qwen3.8)

Real-time multimodal AI pipelines on Apple Silicon

LLM serving engines that SkyDiscover builds on the fly for specific AI models and hardware: Qwen3.6-35B-A3B, Qwen3.8-Flash-Next and Flint on

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

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

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

Free, open-source screen recorder for macOS. A share link the moment you stop, then auto-zoom, smooth cursor and captions under the same lin

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

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

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.

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

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

Local inference you can prove. A single-binary GGUF engine in C: serves, scores, and trains LoRA through the quantized weights it deploys, b

Iris-3B pixel-space text-to-image on Apple Silicon GPUs: Metal-optimized engine, native macOS app, CLI, Python and local HTTP API

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

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

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

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

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

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

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.

Apple Silicon mlx with Zero Dependency Java

neural networks in pure C

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

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

Run GPT-OSS-120B on a 16 GB Mac. Streams mixture-of-experts weights from SSD so only the 2 GiB trunk stays resident. Swift + Metal, no depen

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,

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-

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

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.

TurboQuant MLX: Flagship high-performance model quantization for Apple Silicon. Squeeze maximum inference speed and memory efficiency out of

Interactive terminal coding agent in Rust — runs the DeepSeek V4 Flash model locally on macOS (Metal), with a Ratatui TUI, a full tool suite

Memory-aware GGUF inference runtime with OpenAI-compatible serving

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

🧠 One LLM, split across a Mac (Apple MPS) + a Windows PC (NVIDIA CUDA) — heterogeneous pipeline inference over a framework-neutral wire, bit

Transformer inference via unconventional compute: a single algebraic primitive, a tag-system scheduler, and Apple's Neural Engine through co

Object-storage-native KV cache for LLM inference & RL. Cross-restart, cross-conversation, cross-engine via shared S3 bucket.