Fractional GPU co-location served ~3x more users on Nebius AI Cloud
Company: Nebius
The claim, verbatim
On Nebius AI Cloud, co-locating chat, reasoning, and embedding models on shared GPUs served roughly 3x more total users than dedicated allocation, with combined throughput above 350k tokens per second.
Source (primary)
Open-source NVIDIA Run:ai is now available on Nebius AI Cloud Applications - Nebius (-, news_article)
View cached copy (2026-10-16)Live source ↗Archive.org ↗
Quote: “On Nebius AI Cloud, co-locating chat, reasoning, and embedding models on shared GPUs served roughly 3x more total users than dedicated allocation, with combined throughput above 350k tokens per second.”
How we checked this
Checked on October 17, 2026. The cited source supports every part of this claim.
The post states each of these benchmark figures word for word.
Confirmed in the source:
- The test was run on Nebius AI Cloud
- Chat, reasoning, and embedding models were co-located on shared GPUs
- Co-location served roughly 3x more total users than dedicated allocation
- Combined throughput was above 350k tokens per second
What we did: Read our cached copy of the publisher (https://nebius.com/blog/posts/nvidia-run-ai-open-source-nebius-applications) in full (8,738 characters, retrieved October 16, 2026) and checked each assertion in the claim against it.
Additional evidence
confirms Open-source NVIDIA Run:ai is now available on Nebius AI Cloud Applications - Nebius
Quote: “On Nebius AI Cloud, co-locating chat, reasoning, and embedding models on shared GPUs served roughly 3x more total users than dedicated allocation, with combined throughput above 350k tokens per second.”