All-in-One Package
LLM Runner AIO
All Local LLM Tools — In a Single .exe File
Node.js and Python 3.11 must be installed on your system before running the app.
Share Your FeedbackOverview
LLM Runner AIO is a comprehensive, self-contained desktop application that bundles every tool you need to run local AI models on your own hardware: Open WebUI, llama.cpp, SearXNG, Pi Coding, Vane and optional Wan2GP video generation. No complex setup, no dependency hell — just download, run, and start using AI locally. 100% open source.
What is Included
Open WebUI
MITFrontend interface for chatting with local LLMs
llama.cpp
MITPre-compiled CUDA 13 + Vulkan inference engine
SearXNG
GPLv3Completely private local web search
Pi Coding
Open SourceMinimal agent harness — Web search & Advisor pre-installed (bring your own API key)
Vane
Open SourceWeb search integration — llama.cpp & SearXNG settings pre-configured
Wan2GP
Open SourceOptional AI image/video generation, runs locally — one-click Setup from the System tab
Configured Model Presets
| VRAM | RAM | Models |
|---|---|---|
| 4 / 6 GB | 32 GB | qwen3.6-35B-A3B · gemma-4-26B · gemma-4-E4B |
| 8 GB | 32 GB | qwen3.6-35B-A3B · gemma-4-26B · gemma-4-E4B · qwen3.8-27B |
| 10 GB | 32 GB | qwen3.6-35B-A3B · gemma-4-26B · qwen3.8-27B |
| 12 GB | 32 GB | qwen3.6-35B-A3B · gemma-4-26B · qwen3.8-27B |
| 16 GB | 32 GB | qwen3.6-35B-A3B · gemma-4-26B · qwen3.8-27B |
| 24 GB | 32 GB | qwen3.8-27B · gemma-4-26B |
| 32 GB | 32 GB | qwen3.8-27B · gemma-4-31B |
| 4 GB | 16 GB | gemma-4-E4B · qwen3.5-4B · Ling-3.0-tiny |
| 6 GB | 16 GB | gemma-4-E4B · qwen3.5-9B · Ling-3.0-tiny |
Every model ships with chat, vision and coding profiles. All presets can be added, edited, or removed directly from the GUI — no manual INI editing needed.
Features
No Manual Installation Required
A single 2 GB .exe file — double-click and wait. Everything is set up automatically within a local virtual environment (venv).
Automatic Hardware Detection
Detects your GPU/VRAM and applies the matching hardware profile (VRAM options: 4, 6, 8, 12, 16, 24, 32 GB).
Smart Model Downloader
Select your auto-detection profile and click Model Download — only models that fit your VRAM are downloaded and configured.
GUI Model Manager
Add, edit, or remove models straight from the System tab. Preset INIs are rewritten safely and download URLs stay in sync.
Built-in Video Generation
Wan2GP: install, start, stop and monitor the AI image/video server from the same screen (default port 7860).
Optimized for Coding Agents
Parameters fine-tuned for Qwen and Gemma models to maximize token speed and eliminate formatting or context loop issues.
100% Open Source
You can review the entire source code on GitHub.
How It Works
- llama.cpp runs the AI model inference engine at
http://localhost:1234 - Open WebUI provides the chat interface at
http://localhost:3000 - SearXNG enables local web search at
http://localhost:8080 - Vane handles web search at
http://localhost:3001 - Wan2GP (optional) serves AI image/video generation at
http://localhost:7860
Installation
1
Download
Download LLM-Runner-AIO.exe (2.03 GB) from Hugging Face
2
Run
.exe: double-click to execute. .RAR: extract, then run run.bat first — it installs dependencies, configures Pi Coding and creates a desktop shortcut
3
Detect & Download Models
Click System Detection, then Model Download — models are auto-configured for your VRAM
4
Start Servers
Launch all services and access at http://localhost:3000
System Requirements
| Requirement | Minimum | Recommended |
|---|---|---|
| OS | Windows 10/11 | Windows 11 |
| RAM | 8 GB | 16 GB+ |
| VRAM | N/A | 4 GB+ |
| Python | 3.11 (required) | 3.11 (required) |
| Node.js | Latest (required) | Latest LTS (recommended) |
| Wan2GP (optional) | N/A | Few extra GB disk + CUDA/driver matching your GPU generation |
Note: Python 3.11 and Node.js must be installed on your system before running the app. The optional Wan2GP video service needs a few extra GB of disk space and the CUDA/driver version matching your GPU generation (exact requirements are shown in the setup confirmation window).
Data Privacy
- No Cloud Dependencies — Everything runs locally
- No Telemetry — No data is sent anywhere
- Local Database — Chat history stored only on your machine
- No Account Required — No registration or login needed
Supported Languages
🇹🇷 Turkish🇬🇧 English🇪🇸 Spanish🇩🇪 German🇫🇷 French🇵🇹 Portuguese🇨🇳 Chinese🇯🇵 Japanese
Credits
This project would not be possible without the incredible work of:
- • Georgi Gerganov — llama.cpp
- • Open WebUI Team — Open WebUI
- • SearXNG Contributors — SearXNG
- • All open-source contributors who make local AI accessible
Ready to Get Started?
Download LLM Runner AIO and start running local LLMs instantly.
Share Your Feedback
Loading feedback...