# Together AI runs dedicated B300 inference cluster on IBM Cloud

_Published Tuesday, October 6, 2026 at 4:13 PM EDT · AI, Infrastructure · Latest · Tier 2 — Notable_

![Together AI runs dedicated B300 inference cluster on IBM Cloud — Primary](https://cdn.prod.website-files.com/69654e88dce9154b5f12070c/6ac5547dea69498dca307193_20261060_TAI_IBM_Cloud_and_NVIDIA.png)

Together AI says it is running on a dedicated NVIDIA B300 GPU cluster on IBM Cloud to expand enterprise AI inference capacity. The cluster uses NVIDIA Spectrum-X Ethernet networking and is purpose-built for inference, the process of running trained models to produce outputs.

Together operates the inference layer, IBM supplies the cloud infrastructure, and NVIDIA provides the chips and networking. Together describes itself as the first customer on IBM Cloud's first dedicated, large-scale inference cluster of this kind. The deployment supports its platform for running open models in production.

## Sources

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

---
Canonical: https://techandbusiness.org/newswire/I_qXJz8rbifSHYzGb-fbwI
Published: 2026-10-06T20:13:19.062Z
Story chronology: 2026-10-06T12:00:00.000Z
Retrieved: 2026-10-06T23:09:02.427Z
Publisher: Tech & Business (techandbusiness.org)