Havuz

Reproducible on-device LLM benchmarks for Apple Silicon (iPhone 17 Pro, M4 Max): Apple Core AI, MLX, llama.cpp, LiteRT-LM and Core ML on the

Native Rapid-MLX provider for DeepSeek Harness (dsh) — dsh reads model facts from the server instead of your settings.yaml.

Run Kimi K3 (2.8 T parameters,1.56 TB) on iPhone 16 Pro? Weights stream from your SSD through a memory budget you set. Free, local, on Mac a

An educational macOS app: build and chat with a tiny language model, trained on your Mac

Big models. Small Macs. Zero excuses.

The models on your disk, put to work. A private desktop app for open models — chat, a coding agent built for small models, text-to-image, te

Git-Native Coding Agent for Mac

Run and serve local models headlessly

Free, open-source AI autocomplete for macOS — on-device ghost-text suggestions in every app. A private, local Cotypist alternative built wit

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

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

LLM Steganography: Hide a meaningful text inside another plausible text of comparable length.

System-wide, on-device AI autocomplete for macOS — Copilot-style suggestions in every text field, fully offline and private.

Local-first CLI for benchmarking LLMs on real hardware — quality, speed, reliability, and a real multi-turn agent loop.

Open, calibrated, single-pass typed-decision models (4B & 27B) for finance and trading

Self-hosted Thai AI infrastructure — Mac Mini M4 Pro running TURBO-Fable 27B at 18.5 tok/s for $0.54/day. Fleet of 9 machines, GOD CONFIG v7

Generative image and video runtimes for Apple Silicon (MLX): text/image-to-image, instruction editing, masked edit, text/image/reference-to-

MLX-compatible REAP for pruning MoE models on Apple Silicon

Local, real-time system-audio captioner + translator for macOS — Whisper + a local LLM + a glass overlay. Fully offline.

MLXUI is a Local AI Browser for MLX. Run MLX models AI Workflows.

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

Open, calibrated System 1 decision models: typed choice / score / yes-no answers with a probability for every option. 400M to 80B; CPU, NVID

qMLX: Custom inference engine for Qwen 3.5 122B on Apple Silicon, extending MLX with hybrid attention support, SSD-backed KV cache, and RYS

Macaw — on-device AI agent for macOS. 2.7B LFM2.5 fine-tune, MLX 4-bit, 97 macOS tools, no cloud.

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

macOS 語音聽寫 App — MLX Whisper + Breeze-ASR-25，完全離線，Apple Silicon 最佳化

Personal fork of czlonkowski/simple-meeting-scribe (MIT) — local macOS meeting transcriber: Ukrainian support, summary export (Telegram/Obsi

Symbio is a self fine tuning AI agent that gives power to users through seamless interaction with their machines. This flexible system adapt

A tiered-memory system design for workloads that don't fit in RAM: measure the working set, pin the hot tier, stream the cold tier from flas

A realtime assistant for Mac and Windows. Talk to it and it answers aloud, shows your schedule and mail as cards, and hands longer work to a

The first native Swift inference engine for Gemma 4 on Apple Silicon / iOS

Local AI workstation: chat by voice or text, transcribe, generate images and video (with sound on Apple Silicon), benchmark and serve open-w

Your coding agent starts every session with amnesia — memo fixes that, 100% on your machine. Persistent memory for Claude Code, Codex, Curso

Local LLM chat app for Apple Silicon Macs.

Run the LLM Swarm Router on machines to distribute Local Ai to the Swarm - More Machines - MORE SPEED

Local, open-source Jev alternative: browser agent decisions with Laya (System One model) on your own machine. No cloud, no API key. Playwrig

Community-driven benchmark suite for MLX inference engines on Apple Silicon

train your own chatbot from scratch on a mac

Gemma 4 31B Abliterated — quality-preserving guardrail removal for Google's most capable open model. Apache 2.0. Runs on Apple Silicon via M

A free, local AI image generation studio for Apple Silicon Macs. Run FLUX.2, Krea 2, Z-Image-Turbo, Qwen-Image-2.1-Turbo and SDXL offline on

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.

On-device streaming speech-to-text for macOS, built on Qwen3-ASR via MLX

Which local LLMs can your computer run? Hardware-aware CLI, TUI and GUI: yes/slow/no verdicts and tok/s from your GPU VRAM and RAM, then ver

Native macOS image generator for FLUX.2 Klein — fully on-device on Apple Silicon via MLX. No Python, no ComfyUI, no server.

A native macOS companion for Draw Things: always-visible image and Moodboard inputs, a canvas you can draw on from an iPad (Sidecar), a loca

Run models too big for RAM on Apple Silicon — any Hugging Face model, dense or MoE — by streaming weights from disk

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

Local AI model manager

Spark-optimized MLX LM for local inference and deployment on Apple Silicon

Claude Code의 영구 기억 시스템 — 4-layer 파이프라인 (세션 검색 + 메모리 회수 + Memory Compiler). Karpathy LLM-as-Compiler 패턴 실증판.