# Llama 3.3 models now available on Prompt Engine 🦙

JigsawStack's Prompt Engine just got a major update! We’re excited to announce that Prompt Engine now supports Llama 3.3 70B models. This brings incredible performance improvements and new possibilities for your applications.

## **Why We Are Excited**

Llama 3.3 is a powerhouse. With **405B-level performance in a small 70B package**, it strikes a perfect balance between cost-efficiency and output quality. Whether you’re using Prompt Engine for conversational AI, automating workflows, or analyzing complex data, Llama 3.3 unlocks new capabilities that were previously out of reach.

Try it out [here](https://jigsawstack.com/prompt-engine) – and take a deeper dive into Prompt Engine [here](https://jigsawstack.com/blog/jigsawstack-mixture-of-agents-moa-outperform-any-single-llm-and-reduce-cost-with-prompt-engine)!

![](https://cdn.hashnode.com/res/hashnode/image/upload/v1734043952359/f72aa35c-1198-4dce-9d1d-2098b67bd31b.png align="center")

**Enhanced Speed with Groq Integration**

This upgrade isn’t just about the models—it’s also about speed. **Groq’s inference engine** accelerates model performance to lightning-fast levels, even at scale. Learn more [here](https://jigsawstack.com/blog/groq-jigsawstack-100x-speed-on-every-prompt).

## **What’s Next?**

With this update, we’re making it easier than ever for developers to access the best tools available. Stay tuned for more updates as we continue to push the boundaries of what’s possible with JigsawStack’s Prompt Engine.

Join the conversation on [Discord](https://discord.gg/GnvmdZ7z) and [X](https://x.com/jigsawstack)\- Let us know what you’re building!