tomshardware.com web signal

Nvidia Ships First Vera Rubin AI Platform Samples

6 sources tracking this story
nvidia chips ai infrastructure ai-infrastructure chips

Key insights

  • Nvidia CFO Colette Kress confirmed the first Vera Rubin samples shipped this week, with production shipments targeted for H2 2026.
  • The NVL72 VR200 rack integrates the 88-core Vera CPU, Rubin GPUs with 288 GB HBM4, and BlueField-4 DPUs with SSD-backed key-value cache.
  • ODM partners Foxconn, Quanta, Supermicro, and Wistron are each receiving either complete rack systems or specific silicon samples.

Why this matters

NVIDIA moving from roadmap to physical sample delivery means hyperscalers can now begin their own integration and validation cycles, compressing the timeline to production deployments. The NVL72 VR200's combination of 288 GB HBM4 per Rubin GPU, 128 GB GDDR7 Rubin CPX, and Quantum-CX9 1.6 Tb/s Photonics InfiniBand positions it to compete directly against AMD's Instinct accelerators in hyperscaler data centers. The BlueField-4 DPU with integrated SSD for key-value cache storage signals that NVIDIA is targeting inference-at-scale workloads where KV cache management is a primary performance bottleneck.

Summary

NVIDIA has begun delivering engineering samples of its Vera Rubin AI platform to select hardware partners, with CFO Colette Kress confirming the milestone during the company's earnings call. Sample hardware includes the 88-core Vera CPU, Rubin GPUs with 288 GB of HBM4 each, Rubin CPX GPUs with 128 GB of GDDR7, NVLink 6.0 switching fabric, BlueField-4 DPUs with integrated SSDs for key-value cache storage, and Quantum-CX9 1.6 Tb/s Photonics InfiniBand NICs. Essentially: (NVIDIA, Foxconn, Quanta, Supermicro, Wistron) are in hardware bring-up for NVIDIA's next-generation AI data center platform. - Some partners receive complete NVL72 VR200 racks; others get silicon-only samples to prepare their software and hardware stacks - Production shipments target H2 2026, with the platform positioned to compete against AMD Instinct accelerators in hyperscaler data centers Physical silicon in partner hands marks the real start of Vera Rubin integration work.

Potential risks and opportunities

Risks

  • If production slips to early 2027, hyperscalers that budgeted for Vera Rubin capacity in H2 2026 would need to extend AMD Instinct contracts or delay AI infrastructure expansion plans.
  • ODM partners receiving silicon-only samples rather than complete NVL72 VR200 racks face complex integration work with no published performance targets to validate against.
  • Competitive pressure from AMD's Instinct accelerators could intensify if Vera Rubin production delays give AMD additional time to expand qualification footprints at hyperscalers currently evaluating alternatives.

Opportunities

  • Foxconn, Quanta, Supermicro, and Wistron gain first-mover rack integration expertise for the NVL72 VR200, positioning them ahead of rival ODMs for high-margin production contracts.
  • Networking silicon vendors supplying Spectrum-6 Photonics Ethernet and Quantum-CX9 1.6 Tb/s InfiniBand components are locked in early as the default Vera Rubin interconnect fabric.
  • AI inference software vendors building for BlueField-4 DPU and SSD-backed key-value cache architectures are well-positioned as NVIDIA's inference-at-scale platform enters production.

What we don't know yet

  • Performance benchmarks comparing Vera Rubin to prior NVIDIA generations, including FLOPS, memory bandwidth, and cost per token, were not disclosed in this announcement.
  • Whether named hyperscaler customers such as Microsoft, Google, Meta, or Amazon are among the recipients receiving Vera Rubin samples was not confirmed.
  • Volume ramp timing remains ambiguous: the 'second half of 2026 or early 2027' window spans two distinct planning horizons for hyperscaler capacity commitments.

What others are reporting

Coverage cluster as of 8h after publish

  1. Motley Fool Read →

    Verbatim earnings call transcript capturing Colette Kress's confirmation of sample timing, H2 2026 production schedule, and the six-chip platform's modular serviceability improvements.

    We shipped our first Vera Rubin samples to customers earlier this week, and we remain on track to commence production shipments in the second half of the year.
  2. WCCFTech Read →

    Adds the supply-side cost picture absent from the earnings call framing: HBM4 pricing is driving the VR200 memory bill to $2M of $7.8M total, complicating the 10x efficiency headline.

  3. TechPowerUp Read →

    Hardware-focused trade coverage of the shipment event reaching GPU-specialist readers tracking the Blackwell-to-Rubin transition, likely adding architecture depth and spec tables.

  4. EENews Europe Read →

    Engineering and enterprise trade framing targeting data center operators, focused on the production ramp timeline context for 2026-2027 infrastructure planning decisions.

  5. Windows Report Read →

    Broad technology audience coverage confirming the VR200 sample shipment, reaching readers outside the specialist hardware and financial press covering this event.

Originally reported by tomshardware.com

Read the original article →

Original headline: NVIDIA Ships First Vera Rubin VR200 AI Rack Samples — 50 PFLOPS FP4, 10× Inference Cost Reduction Versus Blackwell