HPE Cray XD675

Accelerate AI workloads with a game-changing, purpose-built architecture.

Run the largest AI models with fewer GPUs

Delivering up to 1307 teraflops of FP16 peak performance with 192GB of HBM3 per GPU, the AMD Instinct™ MI300X can run up to 80 billion parameter LLMs entirely in-memory.

Advance your AI workloads

Go beyond what’s possible and accelerate outcomes as you build and train your own models.

HPE and AMD are your trusted partners for the AI era

Profit from our supercomputing leadership with advanced technology and open architecture to secure your competitive advantage.

Unleash unimaginable performance and efficiency

Tap into the raw power of an 8-way HPC system from the supercomputing industry leader.

Our partners and clients

Take the next steps

Ready to get started? Explore purchasing options or engage with HPE experts to determine the best solution for your business needs.