Blackwell GPU cluster capacity
Company: CoreWeave
The claim, verbatim
CoreWeave provisioned a dynamic cluster with 1,600 NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs and 200 AMD Turin 9655P nodes
Source (primary)
Video Captioning at Scale: 600 TB in 95 Minutes | CoreWeave Blog - CoreWeave (-, news_article)
View cached copy (2026-09-01)Live source ↗
Quote: “CoreWeave provisioned the reservation: a dynamic cluster scaling to 1,600 NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs, 200 AMD Turin 9655P nodes at 192 vCPUs each”
How we checked this
Checked on September 18, 2026. The cited source supports every part of this claim.
The post says CoreWeave provisioned a dynamic cluster scaling to 1,600 of these GPUs plus 200 AMD Turin 9655P nodes. The source's wording is 'scaling to' 1,600 GPUs, which is a ceiling rather than a fixed size.
Confirmed in the source:
- CoreWeave provisioned a dynamic cluster for the run
- The cluster scaled to 1,600 NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs
- The cluster included 200 AMD Turin 9655P nodes
What we did: Read our cached copy of the publisher (https://www.coreweave.com/blog/video-captioning-at-scale-600-tb-in-95-minutes-with-anyscale-on-coreweave) in full (16,024 characters, retrieved September 1, 2026) and checked each assertion in the claim against it.
Additional evidence
confirms Video Captioning at Scale: 600 TB in 95 Minutes | CoreWeave Blog - CoreWeave
Quote: “CoreWeave provisioned the reservation: a dynamic cluster scaling to 1,600 NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs, 200 AMD Turin 9655P nodes at 192 vCPUs each”