---

Private AI chat desktop application with local LLM support.
All inference happens on your machine — no cloud, no data sharing.

Oxide Lab Chat Interface

## 📚 Table of Contents - [What is this?](#-what-is-this) - [Demo](#-demo) - [Key Features](#-key-features) - [Installation & Setup](#️-installation--setup) - [How to Start Using](#-how-to-start-using) - [System Requirements](#️-system-requirements) - [Supported Models](#-supported-models) - [Privacy and Security](#️-privacy-and-security) - [Acknowledgments](#-acknowledgments) - [License](#-license) ## ✨ What is this? Oxide Lab is a native desktop application for running large language models locally. Built with Rust and Tauri v2, it provides a fast, private chat interface without requiring internet connectivity or external API services. ## 🎬 Demo https://github.com/user-attachments/assets/0b9c8ff9-7793-4108-8b62-b0800cbd855e https://github.com/user-attachments/assets/27c1f544-69e0-4a91-8fa5-4c21d67cb7c7 https://github.com/user-attachments/assets/ce5337d5-3e63-4263-b6a7-56e6847bbc71 ## 🚀 Key Features - 100% local inference — your data never leaves your machine - Multi-architecture support: Llama, Qwen2, Qwen2.5, Qwen3, Qwen3 MoE, Mistral, Mixtral, DeepSeek, Yi, SmolLM2 - GGUF and SafeTensors model formats - Hardware acceleration: CPU, CUDA (NVIDIA), Metal (Apple Silicon), Intel MKL, Apple Accelerate - Streaming text generation - Multi-language UI: English, Russian, Brazilian Portuguese - Modern interface built with Svelte 5 and Tailwind CSS ## 🛠️ Installation & Setup ### Prerequisites - Node.js (for frontend build) - Rust toolchain (for backend) - For CUDA: NVIDIA GPU with CUDA toolkit - For Metal: macOS with Apple Silicon ### Development ```bash # Install dependencies npm install # Run with CPU backend npm run tauri:dev:cpu # Run with CUDA backend (NVIDIA GPU) npm run tauri:dev:cuda # Platform-aware development npm run app:dev ``` ### Build ```bash # Build with CPU backend npm run tauri:build:cpu # Build with CUDA backend npm run tauri:build:cuda ``` ### Quality Checks ```bash npm run lint # ESLint npm run lint:fix # ESLint with auto-fix npm run check # Svelte type checking npm run format # Prettier formatting npm run test # Vitest tests ``` ### Rust-specific (from src-tauri/) ```bash cargo clippy # Linting cargo test # Unit tests cargo audit # Security audit ``` ## 📖 How to Start Using 1. Build or download the application 2. Download a compatible GGUF or SafeTensors model (e.g., from Hugging Face) 3. Launch Oxide Lab 4. Load your model through the interface 5. Start chatting ## 🖥️ System Requirements - Windows, macOS, or Linux - Minimum 4 GB RAM (8+ GB recommended for larger models) - For GPU acceleration: - NVIDIA: CUDA-compatible GPU - Apple: M1/M2/M3 chip (Metal) ## 🤖 Supported Models Architectures with full support: - Llama (1, 2, 3), Mistral, Mixtral, DeepSeek, Yi, SmolLM2, CodeLlama - Qwen2/2.5, Qwen2.5/2 MoE - Qwen3, Qwen3 MoE Formats: - GGUF (quantized models) - SafeTensors ## 🛡️ Privacy and Security - All processing happens locally on your device - No telemetry or data collection - No internet connection required for inference - Content Security Policy (CSP) enforced ## 🙏 Acknowledgments This project is built on top of excellent open-source work: - [Candle](https://github.com/huggingface/candle) — ML framework for Rust (HuggingFace) - [Tauri](https://tauri.app/) — Desktop application framework - [Svelte](https://svelte.dev/) — Frontend framework - [Tokenizers](https://github.com/huggingface/tokenizers) — Fast tokenization (HuggingFace) See [THIRD_PARTY_LICENSES.md](THIRD_PARTY_LICENSES.md) for full dependency attribution. ## 📄 License Apache-2.0 — see [LICENSE](LICENSE) Copyright (c) 2025 FerrisMind

Oxide-Lab

Описание

Релизы1

Страницы

Языки

FFerrisMind- 16 фев 2026, 17:13Верифицирован16 фев 2026, 17:13763d520

Релизы
1

F
FerrisMind
-
16 фев 2026, 17:13
Верифицирован
16 фев 2026, 17:13763d520