FriendliAI and Ollama Join Forces to Accelerate Open Model Adoption Among Korean Enterprises

FriendliAI, an AI inference cloud company, and Ollama, an open-source AI developer platform, will meet with leading Korean enterprises and developers to discuss the adoption and real-world use of open models. Ollama co-founders Jeffrey Morgan and Michael Chiang will visit Korea for the events.

The two companies will host separate private events in November for enterprise executives and developers actively working with open models. The discussions will explore how open models can give enterprises greater choice and control over their AI models, data, and infrastructure, as well as how organizations can move from adopting open models to running them in production.

As frontier open-weight models continue to advance rapidly, enterprises have a growing range of AI models to choose from. Enterprises are increasingly looking beyond model performance alone, focusing on how to select models that fit their needs, maintain control over their data and infrastructure, and deploy those models reliably in production.

Ollama and FriendliAI bring complementary strengths to this journey. Ollama enables developers to run leading open models wherever they need them, while maintaining control over their data and scaling from initial experiments to applications serving real traffic. FriendliAI provides the high-performance inference technology and infrastructure needed to run open models fast, reliably, and cost-efficiently at production scale.

Through the events, the two companies will share how enterprises can leverage their respective technologies and ecosystems across the open model process—from exploring and experimenting with models to enterprise adoption and production-scale operation.

The private event for enterprise executives will center on “Open Models & Sovereignty.” Discussions will examine why maintaining choice and control over AI models, data, and infrastructure is becoming increasingly important as enterprises seek to avoid dependency on any single model or service. The event will also examine how enterprises can use Ollama and FriendliAI together to adopt open models and operate them in real-world business environments.

A separate private event for developers will take a more hands-on approach to working with open models. Through demos and technical discussions, participants will see how open models can be applied to real-world products and AI agents, while developers already working with open models will have an opportunity to share their technical experiences, insights, and challenges.

“As open models continue to advance, enterprises have a new opportunity to choose AI that best fits their needs and environments without being tied to a single model or service,” said Byung-Gon Chun, CEO of FriendliAI. “Ollama and FriendliAI bring complementary strengths across the journey—from making open models easy to choose and work with to running them reliably in production. Together with Ollama, we want to help more enterprises consider open models as a practical option and bring them into real-world use.”

“Open models are becoming the foundation for how developers and enterprises around the world build with AI,” said Jeffrey Morgan, co-founder and CEO of Ollama. “In Korea, where AI sovereignty is a national priority, open models give organizations full control over how and where their AI runs. We’re committed to making open models easy and secure for Korean enterprises to adopt and take into production, and we’re glad to have FriendliAI as a partner in that effort.”

[About FriendliAI]

FriendliAI is the fastest inference cloud for agents, built to run frontier open-weight models in production at scale. It delivers up to 7x faster output token speed, up to 90% lower inference costs, and 99.99% uptime across the most demanding agent workloads — long-context inference, real-time streaming, and accurate tool calling. FriendliAI has demonstrated its performance by powering production environments for global partners including Kilo Code and TwelveLabs.

[About Ollama]

Ollama is the easiest way for developers to get up and running with open models. Ollama makes open models easy, efficient, and safe to use, whether they run locally on a user's own device or in Ollama's cloud, and plugs them directly into the tools developers already work with. With 8.9 million monthly active developers, more than 67,000 community-built integrations, and partnerships with every major model lab and hardware vendor, Ollama is the largest developer network in the open model ecosystem. Founded by Jeffrey Morgan and Michael Chiang, Ollama has raised $88M in funding from Benchmark, Theory Ventures, and others.