# Aivres KRS8500 datasheet (parsed) Parsed from Aivres's PDF https://aivres.com/wp-content/uploads/KRS8500V3-Datasheet.pdf on 2026-10-15 (2 pages; OCR and table reconstruction by Reducto; tables are HTML inside this Markdown, images are figure crops from the PDF). Specifications belong to Aivres and are subject to change without notice; the PDF is the authority. Products: [krs8500v3](https://aivres.upstation.io/p/krs8500v3) --- *AIVRES* DATASHEET

figure p1 — 回規回 II XXX TEEE TELE EXE JEEE XXX XXX

KRS8500V3 AI Rack Based on NVIDIA GB300 NVL72 KRS8500V3 is Aivres’ next-generation L11 rack-scale platform, integrating 36 NVIDIA Grace CPUs and 72 NVIDIA Blackwell Ultra GPUs into a fully liquid-cooled architecture. Designed for trillion-parameter LLM training and inference, it delivers unprecedented performance density, scalability, and energy efficiency, setting the foundation for large-scale AI, HPC, and data analytics in data centers worldwide. KRS8500V3 improves on the previous generation KRS8000V3 to establish new MLPerf records and redefine the standard for hyperscale AI computing.

KEY FEATURES Blackwell Ultra Tensor Cores: • 2x attention-layer acceleration, 1.5× AI compute FLOPS uplift • Optimized for trillion-scale LLM and mixture-of-experts (MoE) workloads Expanded HBM3e Memory: • 288GB per GPU, 1.5x higher vs. previous gen • Improved context length support and inference efficiency NVIDIA ConnectX-8 SuperNIC: • Dual-device IO module delivering 800 Gb/s per GPU • Enables high-throughput, low-latency scale-out networking Rack-Scale Liquid Cooling: • Modular CDU options (In-Row / In-Rack / Sidecar) • Full lifecycle DLC service for deployment and operations USE CASES AI Training and Inference Optimized for trillion-scale models, transformer networks, and real-time inference. Big Data Analytics Accelerates data pipelines, reduces storage cost, and improves query performance. Scientific and Engineering Simulations Enhances compute-intensive modeling, from CFD to circuit design.

www.aivres.com Copyright © Aivres. All Rights Reserved. The information contained herein is subject to change without notice. Ver 2.0 Technical Specifications Model: NVIDIA® GB300 NVL72 Configuration: 72 Blackwell Ultra GPUs, 36 Grace CPUs NVLink Bandwidth: 130 TB/s Fast Memory: Up to 40 TB GPU Memory | Bandwidth: Up to 21 TB | Up to 576 TB/s CPU Memory | Bandwidth: Up to 18 TB LPDDR5X | Up to 14.3 TB/s CPU Core Count: 2,592 Arm® Neoverse V2 cores FP4 Tensor Core: 1,080–1,400 PFLOPS (rack-level) FP8/16 Tensor Core: 720 PFLOPS INT8 Tensor Core: 23 PFLOPS FP16/BF16 Tensor Core: 360 PFLOPS TF32 Tensor Core: 180 PFLOPS FP32 Tensor Core: 6 PFLOPS FP64 / FP64 Tensor Core: 100 TFLOPS Rack Specifications Dimensions (W x H x D): 600mm x 2295mm x 1200mm (23.62” x 90.35” x 47.24”) Weight: 1,472–1,487 kg (3,245–3,279 lbs) NVL Config: 72x 1 NV OOB Switch: Option 1: 2 x SN2201_M Option 2: 3 x SN2201_M Option 3: 4 x SN2201_M NVL Cartridge: 4 Rack Type (Per Rack): 9x 1U NVLink Switch Trays 18x 1U Compute Trays 8x 1U Power Shelves Power-Shelf: (6+2)x 33kW Busbar: 1,400A Rack Manifold: Option 1: 44RU, BF Option 2: 44RU, TF CDU: Option 1: L2L In-Row Option 2: L2L In-Rack Option 3: L2A Sidecar Compute Tray Specifications CPU/GPU: 2x Grace CPUs + 4x Blackwell Ultra GPUs Cooling: CPU/GPU/CX8 liquid-cooled, all others air cooled Storage: 8x E1.S NVMe SSDs M.2: 1x M.2 NVMe SSDs Front I/O: 1x USB 3.0, 1x Mgmt I/O, 1x RJ45, 1x Mini Display Port N-S Networking: 1x FHFL PCIe Gen 5 X16 (BF3) E-W Networking: 2x CX8 Mezzanine on board (2x CX8 per Mezzanine) for 4x 800G OSFP Conn Fan: CPU region: 8x 12V 4056 fans with N+1 redundancy Management: DC-SCM BMC management module TPM: Supports TPM 2.0 Switch Tray Specifications Type: NVLink N5500_LD Bandwidth: 14.4TB/s Cooling: 1U liquid cooled Front I/O: 2x RJ45, 1x USB, 1x UART www.aivres.com Copyright © Aivres. All Rights Reserved. The information contained herein is subject to change without notice. Ver 2.0