Ampere Architecture
NVIDIA A40
NVIDIA A40 Datacenter GPU — Rent GPU servers for AI training, inference, and HPC.
Memory
48 GB
GDDR6
FP32
37.4
TFLOPS
Bandwidth
696
GB/s
Avg. Price
$0.75
per hour
Hardware · Specifications
Full specs.
ManufacturerNVIDIA
ArchitectureAmpere
Release Year2020
VRAM48 GB GDDR6
Memory Bandwidth696 GB/s
FP32 Performance37.4 TFLOPS
FP16 Performance74.8 TFLOPS
INT8 Performance299 TOPS
Tensor Cores10752
CUDA/Stream Processors10752
TDP300W
Form FactorPCIe
NVLink SupportNo
Max GPUs per Node4
Compute · Performance
Performance overview.
FP32 Single Precision
37.4
TFLOPS
FP16 Half Precision
74.8
TFLOPS
INT8 Integer Ops
299
TOPS
Workloads · Use Cases
Ideal for.
AI Inference
Graphics Rendering
Virtual Workstations
Data Science
Cost · Pricing
Transparent pricing.
Hourly$0.75/hr
Daily$18.00/day
Monthly$547.50/mo
Platform · Why Runcrate
Why rent NVIDIA A40.
Deploy in 60 Seconds
Get instant access to NVIDIA A40. No setup required, start training immediately.
Pay Per Second
Only pay for what you use. Stop instances anytime. No hidden fees.
Enterprise Ready
99.9% uptime guarantee. 24/7 support. Production-grade infrastructure.
Support · FAQ