Integration Brings Cerebras Inference Capabilities to Hugging Face Hub

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

  • young woman using a smartphone, with digital AI and chat icons overlaid in a blurred academic setting

    Duolingo Embraces AI in Push for Scalable Learning

    Learning platform Duolingo has officially declared itself "AI-first," aiming to make learning replicable, scalable, and always available.

  • stylized AI code and a neural network symbol, paired with glitching code and a red warning triangle

    New Anthropic AI Models Demonstrate Coding Prowess, Behavior Risks

    Anthropic has released Claude Opus 4 and Claude Sonnet 4, its most advanced artificial intelligence models to date, boasting a significant leap in autonomous coding capabilities while simultaneously revealing troubling tendencies toward self-preservation that include attempted blackmail.

  • abstract pattern of cybersecurity, ai and cloud imagery

    OpenAI Report Identifies Malicious Use of AI in Cloud-Based Cyber Threats

    A report from OpenAI identifies the misuse of artificial intelligence in cybercrime, social engineering, and influence operations, particularly those targeting or operating through cloud infrastructure. In "Disrupting Malicious Uses of AI: June 2025," the company outlines how threat actors are weaponizing large language models for malicious ends — and how OpenAI is pushing back.

  • charts, graphs, and shapes

    1EdTech: 6 Keys to Effective Learning Analytics

    1EdTech Consortium has released a free report offering six steps to implementing learning analytics effectively in higher education.