NVIDIA A40
Datacenter
NVIDIA A40

AI Inference and Mainstream Compute for Every Enterprise

  • GPU Architecture: NVIDIA Ampere architecture
  • GPU Memory: 48 GB GDDR6 with ECC
  • Memory Bandwidth: 696 GB/s
  • Interconnect Interface: NVIDIA NVLink (112.5 GB/s bidirectional) and PCIe Gen4 (64GB/s)
$6,295
Add to Cart
Specifications
Specifications
A40
  • CUDA Cores: 10,752 (NVIDIA Ampere architecture-based)
  • RT Cores: 84 (NVIDIA second-generation)
  • Tensor Cores: 336 (NVIDIA third-generation)
  • Peak FP32 TFLOPS (non-Tensor): 37.4
  • Peak FP16 Tensor TFLOPS with FP16 Accumulate: 149.7 | 299.4*
  • Peak TF32 Tensor TFLOPS: 74.8 | 149.6*
  • RT Core Performance TFLOPS: 73.1
Specifications
Specifications
A40
  • Peak BF16 Tensor TFLOPS with FP32 Accumulate: 149.7 | 299.4*
  • Peak INT8 Tensor TOPS: 299.3 | 598.6*
  • Peak INT4 Tensor TOPS: 598.7 | 1,197.4*
  • Form Factor: 4.4" (H) x 10.5" (L), dual slot
  • Display Ports: 3x DisplayPort 1.4; Supports NVIDIA Mosaic and Quadro Sync
  • Max Power Consumption: 300 W
  • Power Connector: 8-pin CPU
  • Thermal Solution: Passive
Specifications
Specifications
A40
  • vGPU Software Support: NVIDIA vPC/vApps, NVIDIA RTX Virtual Workstation, NVIDIA Virtual Compute Server
  • vGPU Profiles Supported: Refer to the Virtual GPU Licensing Guide
  • NVENC | NVDEC: 1x | 2x (includes AV1 decode)
  • Secure and Measured Boot: Yes (optional)
  • NEBS Ready: Level 3
  • Compute APIs: CUDA, DirectCompute, OpenCL, OpenACC
  • Graphics APIs: DirectX 12.0, Shader Model 5.1, OpenGL 4.6, Vulkan 1.1
  • MIG Support: No
Gallery
NVIDIA A40
NVIDIA A40
NVIDIA A40
Test1
Test 2
Test 3
Test 4
Origin
Elgota
Amazon
Best Buy
New Egg
Asus
Noon
Stripe
Amazon Pay
Paypal