I built a one-click installer for local LLMs on Windows: it picks a model for your hardware and sets up Ollama

Description and use

Local AI is a Windows app that automatically detects hardware, recommends a suitable LLM model, installs Ollama and the model, and opens a chat interface with a single click.

Problem

Setting up a local LLM on Windows requires installing Ollama, selecting a suitable model for the hardware, downloading large files, and configuring a UI, which is cumbersome for new users.

Outcome

Local AI reduces the initial setup of a local LLM on Windows to a single click, automatically selecting a model that fits the hardware and providing a ready‑to‑use chat interface.

Workflow

• Run LocalAI.exe
• Detect GPU, VRAM, RAM, and free disk space
• Recommend a model from a catalogue of 34 models based on hardware
• Download and install Ollama (resumable, signature‑checked)
• Pull the recommended model with progress
• Launch chat UI with streaming replies, attachments, and model info
• Optionally move models, update, or uninstall

Evidence

Running an LLM locally is not hard, but the first time is a small quest: install Ollama, figure out which of a hundred models fits your GPU, get the tag right, wait for gigabytes to download, find a UI.

Source

Local AI: a free, open-source (MIT) Windows app that looks at your hardware, picks a model, installs Ollama and the model, and opens a chat.

Source

Detects the GPU, VRAM, RAM and free disk space, and recommends a model from a catalogue of 34

Source

Downloads and installs Ollama without administrator rights, then pulls the model with progress.

Source

Conversations never leave the PC: the chat talks to Ollama on 127.0.0.1.

Source

It is Python plus pywebview (WebView2). main.py starts a local HTTP server on 127.0.0.1 and opens the window; the UI is plain HTML/CSS/JS with no build step.

Source