ChampagneWiki.
AI

Run AI Locally

Self-hosted LLM frontends, inference engines, and open-weight model families for on-device AI.

Offline, Private, Self-Hosted

Run AI Locally.

No sign-ups, no data collection, no internet required. Frontends, engines, and open-weight models you can run entirely on your own hardware.

Pill key: Official / frontier Tool / app Open-source Community Discord Use with caution
Why run AI locally?:

Cloud-based AI providers frequently use your prompts for data collection or model training. Running LLMs locally keeps everything — your prompts, documents, and outputs — entirely on your own machine, with no account, no logging, and no internet connection required once set up.

These are the apps you actually chat through — some are point-and-click desktop apps, others are browser-based UIs pointed at a local backend, and a few are terminal-only for people who want zero overhead.

LM Studio

Desktop App

The most beginner-friendly way to download and run local LLMs, with a built-in model browser and OpenAI-compatible local server.

Ollama

CLI + API

The de facto standard for running open-weight models locally — one command to pull and run a model, plus a REST API that most local-AI tools build on top of.

Open WebUI

Self-Hosted

Feature-rich, ChatGPT-style web interface designed to run entirely offline, with RAG, multi-model support, and a plugin system.

GPT4All

No GPU Needed

Runs quantized local LLMs on ordinary consumer hardware, with a simple desktop chat interface and no internet dependency.


These are the backends that actually load and run the model weights — most frontends above are just a UI layered on top of one of these.

Can I actually run this on my hardware?
  • ModelFit — checks your device against a live model database, ranking which LLMs and coding agents actually run well on your specific GPU or Mac, with dedicated cloud vs. local tool comparisons
  • Can I Run This LLM? — enter your GPU VRAM and system RAM to see which open-weight models actually fit, plus estimated tokens-per-second
  • VRAM Calculator (ApX Machine Learning) — detailed inference and fine-tuning VRAM estimator covering quantization, KV cache, batch size, and multi-GPU offloading
  • As a rule of thumb, a 7B model in 4-bit quantization needs roughly 4 to 6GB of VRAM or unified memory, while a 70B model needs 40GB or more unless heavily quantized

Every family below is open-weight and runs through Ollama, llama.cpp, or LM Studio — pick based on your available RAM and what you're using it for, not just parameter count.

Meta Llama

Most Popular

The most widely adopted open-weight family with the largest community ecosystem, spanning 1B to 405B parameters with strong general reasoning.

Alibaba Qwen

Widest Range

27 models spanning 0.5B to 235B parameters — the widest size range of any family, with strong multilingual and coding performance.

DeepSeek

Best Reasoning

DeepSeek R1 introduced chain-of-thought reasoning that rivals proprietary frontier models, while V3 is a massive but efficient MoE model.

Mistral

Efficient

Known for the best performance-per-parameter ratio in the open-weight space, using sliding window attention for efficiency at smaller sizes.

Google Gemma

Small & Safe

Lightweight family from Google DeepMind spanning 1B to 31B, tuned for strong safety and quality even at small sizes.

Microsoft Phi

Tiny But Sharp

Proves careful training data beats raw parameter count — Phi-4 Mini packs strong reasoning into 3.8B parameters and loads in just 3.2GB.

Smallest viable models
  • SmolLM2 360M — the smallest model in most local databases, loads in about 0.5GB and runs on just 1GB of RAM, including old Macs, iPhones, and embedded boards
  • LFM2 24B-A2B — a sparse mixture-of-experts model that only activates 2B of its 24B parameters per token, fitting in about 14GB and running well on any 16GB Mac
  • Phi-4 Mini 3.8B — loads in 3.2GB and needs just 7GB minimum RAM, making it viable on most modern laptops

If you want an agentic coding assistant without sending code to the cloud, several tools below pair specifically with local models through Ollama rather than requiring a subscription API key.

A note on running agents locally:

Coding agents can execute terminal commands and modify files without additional confirmation if misconfigured. Run them in a container, VPS, or VM rather than on a machine with anything important on it, and avoid giving any agent full drive-root access.


For troubleshooting a specific setup or getting a second opinion on hardware before buying, these communities move faster than most written guides.

On this page