LibreChat
Enterprise self-hosted ChatGPT clone with 30+ AI providers. Multi-user admin panel, OAuth2 SSO, artifacts, code interpreter, and MCP support.
Chat Frontend, Self Hosted
Yes
Yes
Yes
No — runs in the cloud
Enterprise team AI chat with admin controls
Hard
Web, Docker
Open source — free
LibreChat is Enterprise self-hosted ChatGPT clone with 30+ AI providers. Multi-user admin panel, OAuth2 SSO, artifacts, code interpreter, and MCP support. LibreChat (36.8K+ GitHub stars) is the most feature-complete multi-provider chat platform for enterprise and team use.
LibreChat works with both local models and cloud APIs. It supports OpenRouter for unified access to 300+ models from a single API. Ollama integration lets you run models locally on your own GPU. LibreChat is open source (https://github.com/danny-avila/LibreChat), so you can inspect the code and self-host. LibreChat itself needs no GPU. Docker host minimum: 4 GB RAM (2 GB MongoDB + 2 GB app). For local models, add GPU per model requirements. Runs fine on a $5/month VPS with cloud APIs only.
Can it run on my hardware?
Minimum
LibreChat itself needs no GPU. Docker host minimum: 4 GB RAM (2 GB MongoDB + 2 GB app). For local models, add GPU per model requirements. Runs fine on a $5/month VPS with cloud APIs only.
Recommended
8 GB+ system RAM for Docker host. If running local models via Ollama on the same machine, add GPU VRAM per your target model. Consider separate machines for app server and inference server in production.
Approximate VRAM needed for recommended local models at Q4 with 8K context:
| Model | Params | Q4 VRAM | Min GPU |
|---|---|---|---|
| Llama 3.1 70B Instruct | 70B | ~47.1 GB | 48 GB+ |
| Qwen3 235B-A22B (MoE) | 235B | ~149.9 GB | 48 GB+ |
| Qwen3 32B | 32.8B | ~22.2 GB | 24 GB |
App compatibility
| Feature | Supported |
|---|---|
| Local models | Yes |
| OpenRouter | Yes |
| OpenAI-compatible API | Yes |
| Ollama | Yes |
| LM Studio | Yes |
| Anthropic API | Yes |
| Google API | Yes |
| Mistral API | Yes |
| Docker | Yes |
| Works offline | No |
| Needs GPU | No |
Recommended models
Best local models
Local vs cloud: which should you use?
Use local models if
- You want privacy — data never leaves your machine
- You already have a GPU with sufficient VRAM
- You want zero per-token API costs
- You need offline access
Use cloud/API if
- Your GPU has insufficient VRAM for the models you need
- You want access to frontier model quality
- You need maximum coding/reasoning performance
- You don't want to manage local model downloads and updates
- OpenRouter lets you switch between 300+ models with one API key
Setup overview
Setting up LibreChat is complex and requires technical knowledge. It runs on web, docker. Full documentation is available at https://librechat.ai/docs.
Limitations
- Simple single-user setups (use Open WebUI instead)
- Low-resource servers — MongoDB alone needs 2-4 GB RAM
- Quick deployment — Docker Compose with multiple services is complex
Related
Recommended GPUs
Compatible models
Related apps
Frequently asked questions
- What is LibreChat?
- LibreChat is Enterprise self-hosted ChatGPT clone with 30+ AI providers. Multi-user admin panel, OAuth2 SSO, artifacts, code interpreter, and MCP support. LibreChat (36.8K+ GitHub stars) is the most feature-complete multi-provider chat platform for enterprise and team use.
- Does LibreChat need a GPU?
- LibreChat itself does not require a GPU. However, the models you connect to it do. LibreChat itself needs no GPU. Docker host minimum: 4 GB RAM (2 GB MongoDB + 2 GB app). For local models, add GPU per model requirements. Runs fine on a $5/month VPS with cloud APIs only.
- Can I run LibreChat on CPU only?
- Yes — LibreChat supports CPU-only operation, but performance will be significantly slower (5-10x) compared to GPU inference. CPU-only works best for models under 7B parameters with at least 16 GB of system RAM.
- Can LibreChat use OpenRouter?
- Yes. LibreChat supports OpenRouter for accessing 300+ models through a single API. Configure OpenRouter as a provider in LibreChat's settings with your API key.
- Can LibreChat use local models via Ollama?
- Yes. LibreChat works with Ollama for running models locally. Install Ollama, pull your model (e.g., `ollama pull qwen2.5:7b`), and connect LibreChat to the local Ollama server. GPU requirements depend on the model you choose, not LibreChat itself.
- What models work best with LibreChat?
- Models that work well with LibreChat include: Llama 3.1 70B Instruct, Qwen3 235B-A22B (MoE), DeepSeek V3 671B, Llama 4 Maverick 400B. The best model depends on your GPU's VRAM and your use case.
- Is LibreChat free and open source?
- Yes. LibreChat is open source and completely free. You can find the source code on GitHub at https://github.com/danny-avila/LibreChat.