| Sign In | Join Free | My entremaqueros.com |
|
| Sign In | Join Free | My entremaqueros.com |
|
| Categories | Nvidia GPU Server |
|---|---|
| Brand Name: | NVIDIA |
| Model Number: | NVIDIA A30 |
| Place of Origin: | China |
| MOQ: | 1pcs |
| Price: | $490-$520 |
| Payment Terms: | L/C, D/A, D/P, T/T |
| Supply Ability: | 20pcs |
| Delivery Time: | 15-30 word days |
| Packaging Details: | 4.4” H x 7.9” L Single Slot |
| NAME: | Professional Computing Nvidia Ampere A30 GPU Data Center Solution |
| Keyword: | Professional Computing Nvidia Ampere A30 GPU Data Center Solution |
| Model: | NVIDIA A30 |
| FP64: | 5.2 teraFLOPS |
| FP64 Tensor Core: | 10.3 teraFLOPS |
| FP32: | 0.3 teraFLOPS |
| GPU memory: | 24GB HBM2 |
| GPU memory bandwidth: | 933GB/s |
| Form factors: | Dual-slot, full-height, full-length (FHFL) |
| Max thermal design power (TDP): | 165W |
| FP16 Tensor Core: | 165 teraFLOPS | 330 teraFLOPS* |
| INT8 Tensor Core: | 330 TOPS | 661 TOPS* |
| Interconnect: | PCIe Gen4: 64GB/s |
Professional Computing Nvidia Ampere A30 GPU Data Center Solution
GPU Data Center Solution For Scientific Computing
NVIDIA A30 Data Center Solution
The Data Center Solution for Modern IT
The NVIDIA Ampere architecture is part of the unified NVIDIA EGX™
platform, incorporating building blocks across hardware,
networking, software, libraries, and optimized AI models and
applications from the NVIDIA NGC™ catalog. Representing the most
powerful end-to-end AI and HPC platform for data centers, it allows
researchers to rapidly deliver real-world results and deploy
solutions into production at scale.
NVIDIA Tesla A30 leverages groundbreaking features to optimize
inference workloads. It accelerates a full range of precisions,
from FP64 to TF32 and INT4. Supporting up to four MIGs per GPU, A30
lets multiple networks operate simultaneously in secure hardware
partitions with guaranteed quality of service (QoS). And structural
sparsity support delivers up to 2X more performance on top of A30’s
other inference performance gains.
NVIDIA’s market-leading AI performance was demonstrated in MLPerf
Inference. Combined with NVIDIA Triton™ Inference Server, which
easily deploys AI at scale, NVIDIA Tesla A30 brings this
groundbreaking performance to every enterprise.
NVIDIA A30 Data Center Solution
NVIDIA Ampere GPU architecture
24GB HBM2 Memory
Max. Power Consumption: 165W
Interconnect Bus:
PCIe Gen. 4: 64GB/s
3rd NVLink: 200GB/s
Thermal Solution: Passive
Multi-instance GPU (MIG):
4 GPU instances @ 6GB each
2 GPU instances @ 12GB each
1 GPU instance @ 24GB
Virtual GPU (vGPU) software support
NVIDIA A30 Data Center Solution Technical Specifications
GPU Architecture | NVIDIA Ampere |
FP64 | 5.2 teraFLOPS |
FP64 Tensor Core | 10.3 teraFLOPS |
FP32 | 10.3 teraFLOPS |
TF32 Tensor Core | 82 teraFLOPS | 165 teraFLOPS* |
BFLOAT16 Tensor Core | 165 teraFLOPS | 330 teraFLOPS* |
FP16 Tensor Core | 165 teraFLOPS | 330 teraFLOPS* |
INT8 Tensor Core | 330 TOPS | 661 TOPS* |
INT4 Tensor Core | 661 TOPS | 1321 TOPS* |
Media engines | 1 optical flow accelerator (OFA) |
GPU memory | 24GB HBM2 |
GPU Memory Bandwidth | 933 GB/s |
Interconnect | PCIe Gen4: 64GB/s |
Max thermal design power (TDP) | 165W |
Form Factor | Dual-slot, full-height, full-length (FHFL) |
Multi-Instance GPU (MIG) | 4 GPU instances @ 6GB each |
Virtual GPU (vGPU) software support | NVIDIA AI Enterprise for VMware |
|
Leadtek WinFast GS2040T Nvidia GPU Server Dual Port 10GbE
1 VGA 3d Rendering Server Leadtek WinFast GS2040T
Leadtek WinFast WS1040 PC Workstation Server For AI Deep Learning 3D Rendering
48G GDDR6 3xDP 384 Bit Nvidia GPU Server Tesla A40 For Computing Graphics Card Computing Card
Datacenter GDDR6 Nvidia Tesla T4 16GB Scientific Card Deep Learning Edge Inference
4GB Leadtek Quadro Nvidia GPU Server P1000 Computing Graphics Card GDDR5 128bit
High Performance Nvidia GPU Server A10 GPU Accelerator 24GB GDDR6 384bit
NVIDIA Scientific GPU Tesla A100 40GB Workstation Graphic Card
AI Data Center Tesla Tensor Core Nvidia GPU Server A100 80GB Video Graphic Card Computing
Original NVIDIA Quadro P2000 Public GPU For Scientific Computing
