PRIME Intellect
$15M to Build The Open Superintelligence Stack
Authors
Vincent
X
Johannes
X
Announcements
February 28, 2025

$15M to Build The Open Superintelligence Stack

Prime Intellect is building the compute and infrastructure platform to train, evaluate, and deploy agentic models — making it possible for anyone to build frontier AI. We're creating the full stack for open superintelligence: from GPU access to RL training to open research.

Today, we're announcing that we've raised $15M in funding, led by Founders Fund, with participation from Menlo Ventures, Andrej Karpathy (EurekaAI, Tesla, OpenAI), Clem Delangue (Hugging Face), Dylan Patel (SemiAnalysis), Tri Dao (Together.AI), Emad Mostaque (Stability AI), Jake Medwell (8VC Co-Founder) and many others.

This brings our total funding to over $20M, accelerating our work on the open superintelligence stack.

Image

Scaling Open + Democratized AI

Prime Intellect is already operating at scale.

  • Compute: Our Compute Exchange, connects individual developers, startups, cloud providers, and datacenters, creating a distributed GPU marketplace that makes AI compute cheaper and more accessible.
  • Distributed Model Training: We successfully trained a 10B-parameter model across three continents with our PRIME framework , proving that globally-distributed training can match centralized efficiency.
  • Open-Source AI Research:
    • INTELLECT-1, the first 10B-parameter model trained on globally-distributed infrastructure.
    • METAGENE-1, a bio-foundation model for early pandemic detection and global health applications.
    • INTELLECT-MATH, a frontier model for math reasoning trained with RL.
    • GENESYS + SYNTHETIC-1, a distributed RL effort generating the largest synthetic reasoning dataset from DeepSeek-R1.
  • Verifiable Compute: We’ve published TOPLOC, a locality sensitive hashing scheme for efficient verifiable inference.

What's Next

We're scaling every layer of the stack — expanding compute access to more providers and larger clusters, launching hosted evaluations and dedicated inference, and pushing our open research toward ever more capable agentic models. We're also building out RL infra and collaborating with leading open-source AI projects to grow the ecosystem.

Join Us

If you're excited to help shape the future of open-source AI, we'd love to hear from you and invite researchers, engineers, and visionaries worldwide to help build the open superintelligence stack.

  • Collaborate: We're hiring engineers and researchers at the intersection of AI, distributed systems, and open-source development Careers
  • Connect: Follow @primeintellect on Twitter/X or join our Discord community.

A future of truly open superintelligence demands shared effort. Let’s build it together.

‍