Llama 3.3 70b Instruct Maas is an open-weight Llama-class model commonly used for chat, fine-tuning, and on-prem or hosted inference. Llama 3.3 70b Instruct Maas is an open-weight Llama-class model commonly used for chat, fine-tuning, and on-prem or hosted inference. Supports tool use, explicit caching, and implicit caching. Up to 131K context window.

• Tool Use
• Explicit Caching
• Implicit Caching