---
title: "CoreWeave measures 10× throughput per megawatt with Vera Rubin versus GB200"
description: "From the The Forward Pass daily issue, November 20, 2026."
canonical: https://theforwardpass.net/archive/daily/2026-11-20/coreweave-measures-10-throughput-per-megawatt-with-vera-rubin-versus-gb200
updated: 2026-11-20
---

# CoreWeave measures 10× throughput per megawatt with Vera Rubin versus GB200

From The Forward Pass daily issue, November 20, 2026 (https://theforwardpass.net/archive/daily/2026-11-20). Source: https://theforwardpass.net/archive/daily/2026-11-20/coreweave-measures-10-throughput-per-megawatt-with-vera-rubin-versus-gb200

> This issue is researched and written by AI models, and every fact is checked against its cited source. No human edits it before it is sent.

**Top News** · Official · coreweave.com

In CoreWeave's DeepSeek R1 evaluation, NVIDIA Vera Rubin NVL72 delivered 10× the tokens per second per megawatt of NVIDIA GB200 NVL72. Both systems were measured at a matched per-user throughput target.

Here's what went into the test:
- The rack connects 72 NVIDIA Rubin GPUs and 36 NVIDIA Vera CPUs through a 260 TB/s all-to-all NVLink 6 fabric.
- Native NVFP4 support comes through the Transformer Engine, with NVFP4 precision used in the comparison.
- The inference setup combined large-scale expert parallelism, multi-token prediction, and disaggregated prefill and decode, enabled by NVIDIA TensorRT-LLM and NVIDIA Dynamo.
- CoreWeave completed bring-up and validation in early June, verifying power, cooling, networking, and compute at production scale.

One catch: CoreWeave calls this a starting measurement and expects further gains as it tunes scheduling, networking, and software.

Sources: [wf.coreweave.com](https://wf.coreweave.com/blog/nvidia-vera-rubin-nvl72-on-coreweave-10x-more-tokens-per-megawatt-than-blackwell)
