A40 GPU
The A40 combines professional visualization and AI acceleration in a single GPU, supporting virtual workstations and rendering workloads alongside inference tasks. It offers a good balance of memory and compute for mixed graphics and AI use cases.
Starting Price
$0.39/hr
Available on 7 cloud providers
Key Specifications
💾Memory
48GB VRAM
🏗️Architecture
Ampere
⚙️Compute Units
N/A
🧮Tensor Cores
336
Technical Specifications
Hardware Details
ManufacturerNVIDIA
ArchitectureAmpere
CUDA Cores10752
Tensor Cores336
RT Cores84
Compute UnitsN/A
GenerationN/A
Memory & Performance
VRAM48GB
Memory Interface384-bit
Memory Bandwidth696 GB/s
FP32 Performance37.4 TFLOPS
FP16 Performance149.7 TFLOPS
INT8 Performance299.3 TOPS
Performance
Computing Power
CUDA Cores10,752
Tensor Cores336
RT Cores84
Computational Performance
FP32 (TFLOPS)37.4
FP16 (TFLOPS)149.7
INT8 (TOPS)299.3
Common Use Cases
Data center visual computing, AI
Machine Learning & AI
- Training large language models and transformers
- Computer vision and image processing
- Deep learning model development
- High-performance inference workloads
Graphics & Compute
- 3D rendering and visualization
- Scientific simulations
- Data center graphics virtualization
- High-performance computing (HPC)
Market Context
The A40 sits within NVIDIA's Ampere architecture lineup, positioned in the high performance tier.
Cloud Availability
Available across 7 cloud providers with prices ranging from $0.39/hr. Pricing and availability may vary by region and provider.
Market Position
Released in 2020, this GPU is positioned for professional workloads.