Browse and search GGUF models from TheBloke on Hugging Face.
TinyLlama 1.1B - Small and fast
669MB
Microsoft Phi-2 - 2.7B parameters
1.6GB
Mistral 7B Instruct - High quality
4.4GB
Searching models...
💡 Adding Custom Models
Automated: urai add <model-name>
Automatically searches and adds the model from TheBloke's repository
Manual: urai add <model-name> --url <model-link>
Manually specify the exact GGUF file URL