GGUF models: llama4 license
27 GGUF models listed under the llama4 license on Hugging Face. Always read the license text before commercial use. Sizes run from 1.54B to 453B parameters. The longest trained context is 10240K tokens.
About the llama4 license
The license text is in the model repository on Hugging Face. Licenses can differ between a quantized file and the original model, so check both.
27 GGUF models are listed under llama4 on Hugging Face. The most downloaded are Cogito-V2-Preview-Llama-109B-Moe, Llama 4 Scout 17B 16E Instruct Abliterated and Cogito v2 Preview Llama 109B MoE. This is information, not legal advice: always read the license in the repository before you use a model commercially.
Frequently asked questions
Can I use llama4 GGUF models commercially?
The license text is in the model repository on Hugging Face. Licenses can differ between a quantized file and the original model, so check both. Check the license text in the repository and the license of the base model before you build a product on it.