Hardware
Expanding our enterprise inference capacity with IBM Cloud and NVIDIA
Together AI has partnered with IBM and NVIDIA to launch the first dedicated, large‑scale AI inference cluster on IBM Cloud, consisting of NVIDIA B300 GPUs and Spectrum‑X Ethernet networking engineered
Together AI has partnered with IBM and NVIDIA to launch the first dedicated, large‑scale AI inference cluster on IBM Cloud, consisting of NVIDIA B300 GPUs and Spectrum‑X Ethernet networking engineered for high‑throughput inference. The collaboration combines NVIDIA’s advanced GPU silicon, IBM’s mission‑critical cloud infrastructure, and Together AI’s production‑grade inference platform to serve hundreds of trillions of tokens per month for open‑model workloads at enterprise reliability, security, and cost levels. This enables enterprises to run open AI models at scale while keeping sovereign data and achieving frontier‑level performance.
Related
- Together AI is teaming up with @IBM and @nvidia to bring enterprise-grade AI inference to IBM Cloud. A dedicated NVIDIA B300 cluster. Spectr…
- More on our partnership: https://newsroom.ibm.com/2026-08-11-IBM-and-Together-AI-Sign-Multi-Year-Agreement-to-Scale-Open-Source-AI-Inference…
- IBM and Together AI sign a $240M, multi-year deal to build an AI inference cluster on IBM Cloud, using Nvidia's HGX B300 systems, to support open-source models (Anhata Rooprai/Reuters)
Source: Together AI Blog | 2026-10-06