NVIDIA A100 SXM4 80GB
Official
Ampere SXM 2020 7nm
FP32
19.5
TFLOPS
VRAM
80 GB
TDP
400 W
48.8 TFLOPS/kW
Bandwidth
2.0 TB/s
memory
Performance Metrics
Peak theoretical throughput by precision type
| Precision | Peak TFLOPS | Efficiency |
|---|---|---|
| INT8 | 624.0 | 1.560 TFLOPS/W |
| INT4 | 1248.0 | 3.120 TFLOPS/W |
| FP16 | 312.0 | 0.780 TFLOPS/W |
| BF16 | 312.0 | 0.780 TFLOPS/W |
| TF32 | 156.0 | 0.390 TFLOPS/W |
| FP32 | 19.5 | 0.049 TFLOPS/W |
| FP64 | 9.7 | 0.024 TFLOPS/W |
FP16 Efficiency
0.780 TFLOPS/W
312.0 TFLOPS / 400W
FP32 Efficiency
0.049 TFLOPS/W
19.5 TFLOPS / 400W
Power Specifications
TDP
400 W
Max Power
460 W
Power Connector
PCIe 16-pin
Cooling
Liquid
Memory Specifications
Capacity
80 GB
Type
--
Bandwidth
2039 GB/s
Interface
--
Hardware & Design
Form Factor
SXM
Architecture
Ampere
Process Node
7nm
Launch Year
2020
Variant
SXM4 80GB
Market Segment
Data Center
Documentation & Resources
Common Use Cases
LLM Training LLM Inference Scientific Computing HPC Workloads
The NVIDIA A100 is optimized for high-performance computing tasks with Ampere architecture delivering 19.5 TFLOPS of compute power.
Where to Rent
Prices shown are approximate. Click through for current pricing.
Similar GPUs
Systems Using This GPU
Pre-configured systems featuring the NVIDIA A100
| System | Peak Performance |
|---|---|
NVIDIA DGX A100 640GB DGX · rack · 2020 | 4.99 PFLOPS |
NVIDIA HGX A100 4-GPU HGX · baseboard · 2020 | 2.50 PFLOPS |
NVIDIA HGX A100 8-GPU HGX · baseboard · 2020 | 4.99 PFLOPS |
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
Loading verification...
No spam, unsubscribe anytime.