---
title: "Expanding our enterprise inference capacity with IBM Cloud and NVIDIA"
description: "Together AI is collaborating with IBM and NVIDIA to scale enterprise-grade AI inference using a dedicated cluster of NVIDIA B300 GPUs on IBM Cloud with NVIDIA Spectrum-X Ethernet networking. This is the first large-scale inference cluster of its kind on IBM Cloud, and Together AI is the first customer running on it. Together AI operates the inference layer, IBM provides the cloud, and NVIDIA delivers the silicon and networking. The company serves hundreds of trillions of tokens per month to over a million developers, and demand continues to climb. Enterprises choose open models to keep their data sovereign and achieve frontier-level performance at a fraction of closed-model cost."
---

# Expanding our enterprise inference capacity with IBM Cloud and NVIDIA

[Together AI](https://yomu.fyi/company/together-ai) · Oct 6, 2026

**Type:** Announcement

## Summary

Together AI is collaborating with IBM and NVIDIA to scale enterprise-grade AI inference using a dedicated cluster of NVIDIA B300 GPUs on IBM Cloud with NVIDIA Spectrum-X Ethernet networking. This is the first large-scale inference cluster of its kind on IBM Cloud, and Together AI is the first customer running on it. Together AI operates the inference layer, IBM provides the cloud, and NVIDIA delivers the silicon and networking. The company serves hundreds of trillions of tokens per month to over a million developers, and demand continues to climb. Enterprises choose open models to keep their data sovereign and achieve frontier-level performance at a fraction of closed-model cost.

## Context

Together AI, IBM, and NVIDIA are collaborating to provide enterprise-grade AI inference capacity. Together AI operates the inference layer, IBM provides the cloud infrastructure, and NVIDIA supplies the B300 GPUs and Spectrum-X networking. The cluster is purpose-built for inference and is the first of its kind on IBM Cloud.

## Approach / What changed

Together AI is deploying a dedicated, large-scale cluster of NVIDIA B300 GPUs on IBM Cloud, backed by NVIDIA Spectrum-X Ethernet networking, to run its inference platform for open models in enterprise production environments.

## Takeaways

- Together AI, IBM, and NVIDIA have deployed a dedicated B300 GPU cluster on IBM Cloud for enterprise inference, the first such cluster on that platform.
- The cluster uses NVIDIA Spectrum-X Ethernet networking, engineered for high-throughput inference workloads.
- Enterprises choose open models for data sovereignty and frontier-level performance at lower cost compared to closed models.

## FAQ

### What hardware powers the new inference cluster?

The cluster uses NVIDIA B300 GPUs and NVIDIA Spectrum-X Ethernet networking, purpose-built for high-throughput inference.

### What does each company contribute to this collaboration?

Together AI operates the inference platform, IBM provides the cloud infrastructure, and NVIDIA supplies the silicon and networking.

**Tags:** [AI](https://yomu.fyi/topic/ai), [GPU](https://yomu.fyi/topic/gpu), [IBM Cloud](https://yomu.fyi/topic/ibm-cloud), [Inference](https://yomu.fyi/topic/inference), [NVIDIA](https://yomu.fyi/topic/nvidia)

- Source: [Together AI](https://www.together.ai/blog/expanding-our-enterprise-inference-capacity-with-ibm-cloud-and-nvidia)
- Source URL: https://www.together.ai/blog/expanding-our-enterprise-inference-capacity-with-ibm-cloud-and-nvidia
- Ingested by Yomu: 2026-10-06T21:00:10.419Z

[Read original post](https://www.together.ai/blog/expanding-our-enterprise-inference-capacity-with-ibm-cloud-and-nvidia)