# NVIDIA Vera **CPU Rack** CPU for the age of agents at factory scale. [Read the Press Release](https://nvidianews.nvidia.com/news/nvidia-launches-vera-the-cpu-built-to-run-the-worlds-ai-agents) Overview ## Rack-Scale Infrastructure for AI Factories Built on [NVIDIA MGX™](https://www.nvidia.com/en-gb/data-center/products/mgx.md), the NVIDIA Vera CPU Rack delivers dense, liquid-cooled CPU infrastructure for modern [AI factories](https://www.nvidia.com/en-gb/solutions/ai-factories.md). As reinforcement learning and agentic AI systems scale, CPUs run the sandbox environments that execute code, use tools, evaluate results, and analyze data that drives results. The NVIDIA Vera CPU Rack features up to 256 interconnected Vera CPUs and provides a fast path to deploying high-density CPU capacity alongside NVIDIA Vera Rubin NVL72 systems, completing workloads up to 80% faster than traditional CPU infrastructure and helping AI factories generate more tokens per dollar. ### NVIDIA Launches Vera, the CPU Built to Run the World’s AI Agents NVIDIA launches high-performance, energy-efficient NVIDIA Vera CPUs to drive diverse workloads across industries, including agentic AI, reinforcement learning, and data processing. [Read the Press Release](https://nvidianews.nvidia.com/news/nvidia-launches-vera-the-cpu-built-to-run-the-worlds-ai-agents) ### Vera Arrives: NVIDIA’s First CPU Built for Agents Lands at Top AI Labs Ian Buck hand-delivers the first NVIDIA Vera CPU systems to Anthropic, OpenAI, Oracle Cloud Infrastructure, and SpaceXAI—marking the moment agentic CPUs move from announcement to production. [Read the Blog](https://blogs.nvidia.com/blog/vera-cpu-delivery/) Breakthroughs ## CPU Sandboxes Environments for Agentic AI at Scale Reinforcement learning and agentic AI run in continuous feedback loops between models and execution environments. Models generate tokens, code, and queries while CPU-based sandboxes execute actions, evaluate results, and return data for the next step. At scale, thousands to millions of environments run in parallel, often mapped to dedicated CPU cores. Faster per-core performance shortens evaluation cycles, reduces agent wait time, and helps AI factories generate more tokens per dollar. The NVIDIA Vera CPU Rack is purpose-built to scale these environments across AI factories. A single liquid-cooled rack integrates up to 256 Vera CPUs, supporting more than 22,500 concurrent CPU environments. With dense, deployable rack-scale infrastructure, Vera CPU Rack scales CPU capacity alongside NVIDIA Vera Rubin NVL72 systems, keeping evaluation loops short and AI factories operating at peak throughput. Performance ## Industry-Leading Agentic CPU Performance Agentic AI is bottlenecked by traditional CPUs. Across an agent's reasoning loop, the CPU  compiles generated code, runs Python tool chains, and analyzes software code. NVIDIA Vera accelerates all three workloads by up to 1.8x over leading x86 CPUs, turbocharging the agentic inner loop to maximize AI factory output. Relative performance based on measured data, and subject to change. NVIDIA Vera CPU with LPDDR5X performance baselined to latest generation x86 CPU. Features ## Explore the Rack-Scale Breakthroughs Built on NVIDIA MGX, the NVIDIA Vera CPU Rack brings Vera’s agentic AI performance to data-center scale in a dense, liquid-cooled system. With up to 256 Vera CPUs, massive LPDDR5X memory bandwidth, NVIDIA® BlueField®-4 DPUs, and NVIDIA Spectrum-X™ Ethernet networking, Vera CPU Rack gives AI factories a fast path to deploy high-density CPU capacity alongside NVIDIA Vera Rubin NVL72 systems. The result is more concurrent environments, shorter evaluation cycles, and more tokens per dollar. ### Dense CPU Capacity for Agentic AI A single NVIDIA Vera CPU Rack integrates up to 256 Vera CPUs to support more than 22,500 concurrent CPU environments. This gives AI factories the CPU capacity to run sandbox execution, tool use, code workloads, and RL evaluations at the same scale as their GPU infrastructure. ### Liquid-Cooled Deployment at Factory Scale Built on NVIDIA MGX, Vera CPU Rack delivers high-density CPU infrastructure in a ready-to-deploy liquid-cooled rack. It helps AI factories add CPU capacity quickly alongside NVIDIA Vera Rubin NVL72 systems, avoiding the lower density and deployment complexity of scaling only with air-cooled servers. ### Predictable Performance Under Full Load Vera’s fast Olympus cores, LPDDR5X memory, and NVIDIA SCF keep thousands of environments responsive under sustained utilization. Faster per-core execution shortens evaluation cycles, reduces agent wait time, and helps keep GPUs working efficiently. ### Integrated Networking and Offload With NVIDIA BlueField-4 DPUs and Spectrum-X Ethernet, Vera CPU Rack supports the networking, isolation, and infrastructure services needed to run large-scale agentic and RL environments across the AI factory. Technologies ## Inside Vera CPU Rack ### NVIDIA Vera CPU NVIDIA Vera powers the CPU environments behind agentic AI and reinforcement learning, combining fast per-core performance with massive LPDDR5X memory bandwidth to keep sandbox execution, tool use, evaluations, and data workflows moving at AI factory scale. [Build AI Systems With Vera CPUs](https://www.nvidia.com/en-gb/data-center/vera-cpu.md) ### NVIDIA MGX NVIDIA MGX delivers an open modular AI infrastructure that reduces development cost and accelerates time to market across modern data centers. [Accelerate Data Center Innovation With MGX](https://www.nvidia.com/en-gb/data-center/products/mgx.md) ### NVIDIA BlueField-4 NVIDIA BlueField-4 DPUs accelerate data processing across storage, networking, cybersecurity, and elastic scaling in AI factories. [Power AI Factories With BlueField-4](https://www.nvidia.com/en-gb/networking/products/data-processing-unit.md) ### NVIDIA Spectrum-X Ethernet NVIDIA Spectrum-X Ethernet delivers high effective bandwidth, low latency, and performance isolation for AI. The Vera CPU Rack supports rack-scale Spectrum-X Ethernet for higher power efficiency and resiliency. [Unlock High-Performance AI Networking](https://www.nvidia.com/en-gb/networking/spectrumx.md) Specifications1 ## NVIDIA Vera | | NVIDIA Vera CPU | NVIDIA Vera CPU Rack | | --- | --- | --- | | Configuration | 1 NVIDIA Vera CPU | 256 NVIDIA Vera CPUs | | Cores | Threads | 88 custom NVIDIA Olympus cores 176 threads | 22,528 custom NVIDIA Olympus cores (88 per CPU) | 45,056 threads (176 per CPU) | | L2 Cache (per core) | 2 MB | 2 MB | | Unified L3 Cache | 164 MB | 42 GB (164 MB per CPU) | | SIMD (per core) | 6x 128bSVE2 FP8 | 6x 128bSVE2 FP8 | | Memory Capacity | Up to 1.5 TB SOCAMM LPDDR5X | Up to 400 TB2 SOCAMM LPDDR5X | | Peak Memory Bandwidth | Up to 1.2 TB/s | Up to 300 TB/s aggregate | | NVIDIA NVLINK™-C2C Bandwidth | 1.8 TB/s | 1.8 TB/s per CPU | | PCIe CXL | 88 PCIe Gen 6 (CPU-only) 96 PCIe Gen 6 (Vera Rubin) x16, x8, x4, x2 bifurcation CXL 3.1 | Up to 22,528 lanes PCIe Gen 6 total; CXL 3.1 | | NIC | BlueField-4 CX9 Any compatible PCIe NIC | 64x PCIe gen Xx with support for NVIDIA BlueField-4 DPUs | | Confidential Computing | Yes | Yes | | Form Factor and Cooling | 1S and 2S Server Air or liquid cooled 250 W to 450 W Configurable TDP | 48U MGX Rack 100% liquid cooled | 1. Preliminary information. All values are up to and subject to change. 2. 200 TB recommended config. **Partners** ## Meet Our Partners **Get Started** ## Stay Up to Date on NVIDIA News Sign up for the latest news, updates, and more from NVIDIA. [Stay Informed](https://www.nvidia.com/en-gb/preferences/email-signup.md)