Llama 3.1

Llama 3.1 models

405B

Flagship foundation model driving widest variety of use cases.

70B

Highly performant, cost effective model that enables diverse use cases.

8B

Light-weight, ultra-fast model you can run anywhere.

Key capabilities

Start building more advanced use cases, leveraging our resources.

• Tool use

• Multi-lingual agents

• Complex reasoning

• Coding assistants

Make Llama your own

Using our open ecosystem, build faster with a selection of differentiated product offerings to support your use cases.

Inference

Choose from real-time inference or batch inference services. Download model weights to further optimize cost per token.

Fine-tune, Distill & Deploy

Adapt for your application, improve with synthetic data and deploy on-prem or in the cloud.

RAG & Tool Use

Use Llama system components and extend the model using zero shot tool use and RAG to build agentic behaviors.

Synthetic Data Generation

Leverage 405B high quality data to improve specialized models for specific use cases.