Пропустить и перейти к галереям изображений

Перейти к началу галереи изображений

NVIDIA-A30, A30 Tensor Core Data Center GPU, 24GB HBM2, PCIe Gen4

Бренд: Nvidia
Модель: Nvidia A30
In Stock
- United States
- United Kingdom
- Germany
- United Arab Emirates
- Singapore
- India
- Hong Kong

4 279,00 US$

Price Alert

100% Genuine

Original, factory-verified

3-Year Warranty

Extended, enterprise-grade

24 Years Expertise

Proven, deployment-focused

Condition

Original New

Экспресс-доставка в Соединенные Штаты
Estimated shipping time: 2–6 business days via DHL, FedEx, UPS and more

Certified Expertise Builds Trust

CCIE · JNCIE · NSE7 · ACDX · HPE Master ASE · Dell Server/AI Expert

Talk to an Expert

Faster Delivery, Globally Ready
20+ years of supply chain expertise for faster multi-stop delivery with smooth customs.
48H Worldwide Shipping
10+ Global Warehouses
Keep Projects On Time
Reliable availability and real-time shipment visibility to keep every critical IT project on schedule.
Отследить ваш заказ

Leading Global Distributor
Since 2002
A global ICT bridge delivering authentic hardware and trusted service for over 20 years.

Worry-Free Coverage with RSCare
3-Year warranty for enterprise hardware, including advanced RMA, diagnostics, spare parts support, and OEM service compatibility.
Cisco SmartNet
HPE Foundation Care
Dell ProSupport
Juniper Care
Fortinet Support
Your Trusted Genuine Source
Authorized partnerships with 30+ brands, including Cisco, HPE, Dell, Juniper, and Fortinet.
100% Authentic Products
100,000+ Multi-Brand SKUs Available

NVIDIA-A30, A30 Tensor Core Data Center GPU, 24GB HBM2, PCIe Gen4

100% Genuine Ready to Ship

4 279,00 US$

Обзор

Nvidia Nvidia A30 Обзор

The NVIDIA A30 is an Ampere-based data center GPU with 24GB HBM2 memory for AI inference, high-performance computing, and virtualized data center workloads.

Key Specifications

GPU Memory

24GB HBM2

Memory Bandwidth

Up to 933GB/s

PCIe Interface

PCIe Gen4 x16

MIG Support

Up to 4 GPU instances

Form Factor

Full-height, full-length, dual-slot

Maximum Power

165W

Best Fit Applications

AI Inference

The A30 combines 24GB HBM2 memory, Tensor Core acceleration, and up to 4 MIG instances for partitioned data center AI inference workloads.

HPC and Data Center Compute

PCIe Gen4 connectivity, 933GB/s memory bandwidth, and 165W power support compute-intensive HPC and scale-out data center applications.

GPU Virtualization

Support for NVIDIA Virtual Compute Server and NVIDIA AI Enterprise enables virtualized GPU resources for compatible server environments.

NVIDIA A30 PCIe Card Layout

This technical layout shows the NVIDIA A30 PCIe card structure and major installation-related areas, helping verify card orientation and server integration requirements.

NVIDIA A30 Card Dimensions

Use this dimensional drawing to check the full-height, full-length, dual-slot card clearance and the required server space before installation.

NVIDIA A30 CPU 8-Pin Power Connector

This diagram identifies the CPU 8-pin auxiliary power connector and helps confirm that the target server provides the required power connection.

NVIDIA A30 NVLink Deployment

This deployment diagram shows two adjacent NVIDIA A30 GPUs connected by one NVLink Bridge, helping users check slot spacing and multi-GPU installation requirements.

Compare Related Models

	NVIDIA A30	NVIDIA T4	NVIDIA A10	NVIDIA A100-80G	NVIDIA A40
GPU Architecture	Ampere	Turing	Ampere	Ampere	Ampere
GPU Memory	24GB HBM2	16GB GDDR6	24GB GDDR6	80GB HBM2e	48GB GDDR6 ECC
Memory Bandwidth	933GB/s	320GB/s	600GB/s	1,935GB/s	696GB/s
FP32 Performance	10.3 TFLOPS	8.1 TFLOPS	31.2 TFLOPS	19.5 TFLOPS	37.4 TFLOPS
INT8 Performance	330 / 661 TOPS with sparsity	130 TOPS	250 / 500 TOPS with sparsity	624 / 1,248 TOPS with sparsity	299.3 / 598.6 TOPS with sparsity
PCIe Interface	PCIe Gen4 x16; 64GB/s	PCIe Gen3 x16; 32GB/s	PCIe Gen4 x16; 64GB/s	PCIe Gen4 x16; 64GB/s	PCIe Gen4 x16; 64GB/s
NVLink	Up to 200GB/s; one bridge for two adjacent A30 GPUs	Not listed in the official product data	Not listed in the official product data	600GB/s with NVLink Bridge	112.5GB/s bidirectional
MIG Support	Up to 4 instances: 4 x 6GB, 2 x 12GB, or 1 x 24GB	Not specified in the official product data	Not specified in the official product data	Up to 7 instances at 10GB each	Not specified in the official product data
Form Factor	Full-height, full-length, dual-slot	Low-profile PCIe	Full-height, full-length, single-slot	Dual-slot PCIe; air-cooled or liquid-cooled variants	Full-height, full-length, dual-slot
Cooling Solution	Passive	Passive	Passive	Air-cooled or liquid-cooled	Passive
Maximum Power	165W	70W	150W	300W	300W
Best-Fit Workloads	AI inference, HPC, GPU virtualization, and MIG-partitioned data center workloads	Low-power AI inference, video analytics, VDI, and edge servers	AI inference, graphics rendering, video transcoding, and VDI	Large-model AI training, HPC, large-memory inference, and multi-GPU computing	Professional visualization, simulation, AI, data science, and virtual workstations

System Compatible Components

Type	Part Number	Description
Mounting Extender	682-00007-5555-000	NVIDIA A30 long offset extender; the card and extender assembly measures 339 mm.
Mounting Extender	682-00007-5555-001	NVIDIA A30 straight extender; the card and extender assembly measures 312 mm.

Сертификаты качества

Спецификация

Nvidia Nvidia A30 Спецификация

Product Type	Data Center GPU
Brand	NVIDIA
Model / Catalog SKU	NVIDIA A30 / NVIDIA-A30
NVIDIA Product SKU	P1001 SKU 205
Architecture	NVIDIA Ampere
PCI Device ID	0x20B7
Vendor ID	0x10DE
Sub-System ID	0x1532
GPU Clocks	Base: 930 MHz; Boost: 1440 MHz
Performance State	P0
UEFI	Supported
GPU Memory	24GB HBM2
Memory Clock	1215 MHz
Memory Bus Width	3072-bit
GPU Memory Bandwidth	Up to 933GB/s
ECC Support	Enabled by default; can be disabled via software
Peak FP64 Performance	5.2 TFLOPS
Peak FP64 Tensor Core Performance	10.3 TFLOPS
Peak FP32 Performance	10.3 TFLOPS
TF32 Tensor Core Performance	82 TFLOPS / 165 TFLOPS with sparsity
BF16 Tensor Core Performance	165 TFLOPS / 330 TFLOPS with sparsity
FP16 Tensor Core Performance	165 TFLOPS / 330 TFLOPS with sparsity
INT8 Tensor Core Performance	330 TOPS / 661 TOPS with sparsity
INT4 Tensor Core Performance	661 TOPS / 1,321 TOPS with sparsity
Media Engines	1 optical flow accelerator (OFA) 1 JPEG decoder (NVJPEG) 4 video decoders (NVDEC)
PCI Express Interface	PCIe Gen4 x16; 64GB/s
PCIe Features	Lane polarity inversion and lane reversal supported
NVLink	Third-generation NVIDIA NVLink; up to 200GB/s with an NVLink Bridge for up to two GPUs
NVLink Bridge Support	One bridge supported; connects one NVIDIA A30 GPU to one adjacent NVIDIA A30 GPU
NVLink Speed and Bandwidth	1 supported bridge; 32 total Rx and Tx lanes; 50Gbps per lane in each direction; up to 200GB/s total bandwidth
NVLink Installation Clearance	At least 2.5mm above the card north edge and 2.67mm behind the rear PCB
NVLink CPU Topology	In multi-CPU systems, bridged A30 cards should generally be within the same CPU domain
Multi-Instance GPU (MIG)	4 MIGs at 6GB each; 2 MIGs at 12GB each; or 1 MIG at 24GB
SR-IOV Support	Supported; 8 virtual functions
Virtual GPU Software Support	NVIDIA AI Enterprise; NVIDIA Virtual Compute Server
Unified Virtual Memory	Supported
Page Migration Engine	Supported
Linux Driver Support	R460.65 or later
Windows Driver Support	R461.98 or later
CUDA Support	CUDA 11.3 or later
vGPU Software Version	vGPU 13.0 or later
NVIDIA AI Enterprise	Supported with VMware
NGC-Ready Test Suite	NGC-Next Certification 2.2 or later
Secure Boot	Supported
Hardware Root of Trust	Supported; some A30 boards also include a secondary CEC1712 root-of-trust device
Security Firmware Features	Secure firmware upgrade, firmware rollback protection, and secure application processor recovery
NEBS Readiness	Supported
Form Factor	Full-height, full-length (FHFL), dual-slot, 10.5-inch PCIe card
Thermal Solution	Passive; requires system airflow
Airflow Direction	Bidirectional heat sink; supports left-to-right or right-to-left airflow
Total Board Power / Maximum TDP	165W
Power Connector	One CPU 8-pin auxiliary power connector
Supported Auxiliary Power Connections	1 x CPU 8-pin cable CPU 8-pin to PCIe 8-pin cable adapter
Power Management	Programmable power cap supported through NVIDIA tools including nvidia-smi and SMBPBI
Dimensions	268.60mm length with I/O bracket; 267.70mm length without I/O bracket; 111.15mm overall height; 104.86mm board height
Board Weight	1,240g, excluding bracket, extenders, and NVLink Bridge
Packaged Weight	10kg
Component Weights	NVLink Bridge: 20.5g; bracket with screws: 20g; long offset extender: 64g; straight extender: 39g
Long Offset Extender	NVPN 682-00007-5555-000; card plus extender length: 339mm
Straight Extender	NVPN 682-00007-5555-001; card plus extender length: 312mm
Ambient Operating Temperature	0°C to 55°C
Short-Term Operating Temperature	-5°C to 55°C; maximum 96 consecutive hours and no more than 15 days per year
Storage Temperature	-40°C to 75°C
Operating Humidity	5% to 85% relative humidity
Short-Term Operating Humidity	5% to 93% relative humidity
Storage Humidity	5% to 95% relative humidity
Altitude Condition	Specifications applicable up to 6,000 feet
Safety and Environmental Compliance	WHQL, EU RoHS, REACH, WEEE, and Halogen Free
EMC and Regulatory Agencies	RCM, BSMI, CE, FCC, ICES, KCC, cUL/UL, and VCCI

Still unsure about your config? Talk to an engineer →

Сертификаты качества

Need Help? Technical Experts Available Now.

+1-626-655-0998 (USA)
UTC 15:00-00:00
+852-2592-5389 (HK)
UTC 00:00-09:00
+852-2592-5411 (HK)
UTC 06:00-15:00

Get a Quote

Live Chat

Need Help? Technical Experts Available Now.

Отзывы покупателей

Напишите свой собственный отзыв

Only registered users can write reviews. Please Sign in or create an account

Гарантия

Your Trusted Global ICT Partner
Delivering reliable, cross-border fulfillment with 20+ years of expertise, backed by rigorous QC, fast logistics, and worldwide warehousing.
Global warehousing
10+ hubs positioned for fast international dispatch and stable availability.
Seamless cross-border
QC-verified packing and predictable delivery via FedEx, DHL, UPS.
ICT Tools Hub for Confident Monitoring
Stay informed on product lifecycle status and real-time inventory availability—supporting confident planning, sourcing, and operational execution.
EOL/EOSL Checker
Verify product lifecycle status to plan purchases and avoid EOL/EOSL risks.
Request VIP Inventory Portal Access
Connect via live chat for VIP access to real-time inventory on priority SKUs.
Certified Experts Across Leading Vendors
Professional guidance for network, security & data center builds, delivered by certified experts with extensive, hands-on deployment experience.
Multi-vendor engineering
Certified expertise across Cisco, HPE, Aruba, Dell, Juniper, Huawei and Fortinet.
Deployment-ready guidance
Faster, safer rollouts with project-focused engineering guidance.

The Choice of 21,500 +Global Customers

Industry-Leading Warranty Coverage You Can Trust

100% Low Price Guarantee
Router-switch.com offers genuine, high-quality ICT products at competitive wholesale prices—ensuring exceptional value without compromising quality.
100% Quality Assurance
All items are brand new, original, and factory-sealed.
Upon request, each unit can be fully tested and verified by a Nvidia-certified engineer to ensure perfect working condition before shipment.
100% Money-Back Guarantee
If you are not satisfied with your purchase, you may request an exchange or full refund. Our customer service team will guide you through the return process quickly and smoothly.
Visit Политика в отношении возвращения page for more information.
Free Nvidia Техническая поддержка
Our Nvidia-certified experts provide free professional support via phone, email, online chat, or remote login—helping you deploy and troubleshoot with confidence.
Flexible & Secure Payment and Shipping
We support multiple secure payment and logistics options, backed by industry-leading verification:
Оплата банковским переводом.

Оплатите с помощью PayPal.

Оплата кредитной картой Visa.

Оплата кредитной картой Mastercard.

Платите картой Discover.

Pay by American Express.
More
Trusted & Secure Payments ×
100% Trusted, Secure Purchase at Router-switch.com
120+ Local Currencies

Multiple Payment Options

100% Secure Payments
Choose the payment method that works for you—local options, multiple currencies, or bank transfers. Every payment is protected by SSL encryption, PCI DSS-level security, McAfee Secure, and VeriSign Secured for complete peace of mind.

Guaranteed Safe Checkout

View Payment Options
Visit How to Pay page for more information

Warranty Coverage & RMA Instructions

Extended, Worry-Free Warranty Coverage
- Factory New Sealed Enterprise Hardware: 3 Years
- Factory New Sealed Consumer Devices: 1 Year
Visit Гарантийная политика page for more information
How to Get Support
If you encounter issues with products, please reach out to your dedicated sales representative. They will assist with diagnostics, remote troubleshooting, and RMA processing if necessary.
Visit Обратная связь page for more support options.