HomeTechHardwareNvidia Details Vera Rubin Maximization
HARDWARE

Nvidia Details Vera Rubin Maximization of Intelligence per Dollar

Nvidia outlined how its Vera Rubin platform targets continuous post-training workloads to increase intelligence per dollar for agentic AI.

WHAT YOU NEED TO KNOW
  • Vera Rubin trains the largest models with one-fourth the GPUs of the Blackwell generation.
  • Nemotron 3 Ultra achieved a 71.7% score on the SWE-bench verified coding benchmark.
  • Prime Intellect reported 30% higher throughput per CPU on Nvidia Vera compared to alternative x86 architectures.
  • Perplexity uses an RDMA engine to transfer trillion-parameter weights in under two seconds between nodes.

Nvidia announced details on how its Vera Rubin architecture optimizes post-training workloads for agentic artificial intelligence models. The company stated that agentic models require continuous refinement post-deployment rather than a single initial training run, shifting compute demand toward ongoing learning cycles.

Pretraining teaches a model fluency by predicting the next token, whereas post-training builds intelligence by teaching models to write code, execute multistep plans, and recover from mid-run errors. According to Nvidia, this continuous refinement relies on reinforcement learning techniques where a model attempts a task during a forward pass, receives a score, and updates its weights during a backward pass across millions of repetitions.

Cost per token measures the operational cost of inference, while intelligence per dollar measures the overall return on investment in model capabilities. Nvidia noted that software libraries like NeMo Gym and NeMo RL standardize these post-training workflows across thousands of parallel environments.

Hardware and Performance

Nvidia built its open-weight, 550-billion-parameter Nemotron 3 Ultra model using a mixture-of-experts design and a disclosed NeMo RL post-training recipe. The model achieved a 71.7% score on the SWE-bench verified benchmark by resolving software bugs from open-source projects.

The upcoming Vera Rubin platform trains the largest AI models using one-fourth as many GPUs as the preceding Blackwell platform. Nvidia designed the architecture specifically to support continuous rollouts and parallel environments required by agentic post-training.

Deployment and Infrastructure

Prime Intellect optimized its sandbox infrastructure for Nvidia Vera CPUs, reporting an average 30% throughput increase per CPU over alternative x86 architectures during realistic reinforcement learning workloads. Meanwhile, Perplexity operates an asynchronous post-training stack using hundreds of Nvidia GPUs and an RDMA-based transfer engine that syncs trillion-parameter models between training and inference nodes in under two seconds.

Together AI offers post-training services—including supervised fine-tuning, reinforcement learning, and direct preference optimization—on Nvidia hardware via its AI Native Cloud platform, with plans to adopt the Vera Rubin platform next.

Xentir Media
Xentir Media NewsroomSource-backed AI and technology coverage, drafted by Xentir's automated editorial system under fixed human-set rules. See our editorial policy and AI usage policy.
J
Jomon · Founder & EditorFounder and editor of Xentir Media. Sets the editorial rules the newsroom system runs under, and is accountable for its corrections. About Jomon · [email protected]
The Xentir Brief
The developments worth knowing — one useful email.
Get the Brief →
IN THE AI INDEX

Models named in this story, with their current rank on the index:

Nemotron 3 Ultra · #69 overallSee the full AI Model Rankings →