Add as a preferred source on Google


Integration Brings Cerebras Inference Capabilities to Hugging Face Hub

  • By John K. Waters
  • 03/14/25

AI hardware company Cerebras has teamed up with Hugging Face, the open source platform and community for machine learning, to integrate its inference capabilities into the Hugging Face Hub. This collaboration provides more than 5 million developers with access to models running on Cerebras' CS-3 system, the companies said in a statement, with reported inference speeds significantly higher than conventional GPU solutions.

Cerebras Inference, now available on Hugging Face, processes more than 2,000 tokens per second. Recent benchmarks indicate that models such as Llama 3.3 70B running on Cerebras' system can reach speeds exceeding 2,200 tokens per second, offering a performance increase compared to leading GPU-based solutions.

"By making Cerebras Inference available through Hugging Face, we are enabling developers to access alternative infrastructure for open source AI models," said Andrew Feldman, CEO of Cerebras, in a statement.

For Hugging Face's 5 million developers, this integration provides a streamlined way to leverage Cerebras' technology. Users can select "Cerebras" as their inference provider within the Hugging Face platform, instantly accessing one of the industry's fastest inference capabilities.

The demand for high-speed, high-accuracy AI inference is growing, especially for test-time compute and agentic AI applications. Open source models optimized for Cerebras' CS-3 architecture enable faster and more precise AI reasoning, the companies said, with speed gains ranging from 10 to 70 times compared to GPUs.

"Cerebras has been a leader in inference speed and performance, and we're thrilled to partner to bring this industry-leading inference on open source models to our developer community," commented Julien Chaumond, CTO of Hugging Face.

Developers can access Cerebras-powered AI inference by selecting supported models on Hugging Face, such as Llama 3.3 70B, and choosing Cerebras as their inference provider.

About the Author

John K. Waters is the editor in chief of a number of Converge360.com sites, with a focus on high-end development, AI and future tech. He's been writing about cutting-edge technologies and culture of Silicon Valley for more than two decades, and he's written more than a dozen books. He also co-scripted the documentary film Silicon Valley: A 100 Year Renaissance, which aired on PBS.  He can be reached at [email protected].

Featured

  • hooded figure types on a laptop, with abstract manifesto-like posters taped to the wall behind them

    Hacktivism Is a Growing Threat to Higher Education

    In recent years, colleges and universities have faced an evolving array of cybersecurity challenges. But one threat is showing signs of becoming both more frequent and more politically charged: hacktivism.

  • Hand holding a stylus over a tablet with futuristic risk management icons

    Why Universities Are Ransomware's Easy Target: Lessons from the 23% Surge

    Academic environments face heightened risk because their collaboration-driven environments are inherently open, making them more susceptible to attack, while the high-value research data they hold makes them an especially attractive target. The question is not if this data will be targeted, but whether universities can defend it swiftly enough against increasingly AI-powered threats.

  • digital book with circuit patterns

    Turnitin and ACUE Partner on AI Training for Educators

    Turnitin is teaming up with the Association of College and University Educators to create a series of courses on AI and academic integrity designed to help faculty navigate the responsible use of AI in learning and assessment.

  • student with headphones engaged in virtual learning

    Virtual Learning that Works: 4 Ways to Build Real Engagement

    As colleges and universities expand online offerings, the goal now is clear: Build environments where students actively participate, not passively attend.