Together AI, the leading AI acceleration cloud, empowers developers and businesses to seamlessly design, develop, and manage their entire generative AI lifecycle on open source models like Llama.

To inspire developers who build on Llama, Together AI built the LlamaCoder app—an open source web app that allows people to generate an entire app from a prompt using Llama 3.1 405B.

In just over a month since its release, Together AI has a viral hit on its hands. More than 2,000 GitHub stars and hundreds of developers have cloned the repository, and more than 200,000 apps have been generated using LlamaCoder.

“Developers are loving it,” says Hassan El Mghari, a software engineer leading developer relations at Together AI. “It was incredible to see people generating quiz apps, pomodoro timers, budgeting apps, and more and making it their own—simply with prompting. It really shows the power of Llama 3.1 405B.”

Llama 3.1 405B was the first open source model capable of performing well in this specific coding use case, he adds. Together AI has also developed a variety of other example apps that use Llama 3.1, including LlamaTutor, an app designed to help people learn, andTurboSeek, an AI-powered search engine.

“Llama models have pushed the boundaries of open source LLMs, rivaling the best closed source models, while providing safety tools for responsible development,” El Mghari says. He adds that Llama 3.1 405B’s state-of-the-art capabilities in general knowledge, steerability, math, tool use, and multilingual translation have the potential to rapidly accelerate developer and enterprise adoption of open source AI.

More than 150,000 developers and companies use the Together platform for a wide range of use cases, including gaming, customer service, benchmarks, and summarization. While they use the Together platform to power their generative AI applications, each developer and company keeps ownership of their fine-tuned weights and can download them for other use cases.

“Our vision is to bring innovations from research to production the fastest. Built on our leading inference optimization research, the Together Inference Engine leverages innovations including FlashAttention-3 kernels, custom-built speculators based on RedPajama, and the most accurate quantization techniques available on the market,” El Mghari says. “These advancements enable developers to build and run generative AI applications on Llama 3.1 models with unmatched performance, accuracy, and cost-efficiency at production scale.”

All of this is made possible by taking an open approach. El Mghari says that many of the companies that use Together AI switched over from closed source providers because they’re eager to reap the benefits of open source.

“Open source AI has been a game changer for the AI community,” he says. “It is in the best interest of all developers and will lead to the fastest advancement and innovation. And beyond all of that, it enables organizations to truly own their data, their models, and have that full flexibility instead of getting locked in.”