NVIDIA A100 SXM4 40GB
Performance
Peak theoretical throughput by precision type
| Precision | Dense | 2:4 Sparse |
|---|---|---|
FP64 64-bit floating point | 9.7TFLOPS | Structured sparsity is a tensor-core feature; this vector precision has no sparse form |
FP32 32-bit floating point | 20TFLOPS | Structured sparsity is a tensor-core feature; this vector precision has no sparse form |
TF32 TensorFloat-32 | 156TFLOPS | 312TFLOPS |
BF16 Brain Float 16 | 312TFLOPS | 624TFLOPS |
FP16 16-bit floating point | 312TFLOPS | 624TFLOPS |
FP8 | No verified data available | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
FP6 | No verified data available | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
FP4 | No verified data available | The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision |
INT8 8-bit integer | 624TOPS | 1,248TOPS |
INT4 4-bit integer | 1,248TOPS | 2,496TOPS |
Dense peak divided by accelerator TDP. Board power only: excludes host CPUs, networking, cooling and facility overhead. TDP for this part: 400 W.
The A100 SXM4 40GB in the GPU landscape
Peak FP16 TFLOPS (dense) against TDP, single-GPU parts tracked by Flopper
Higher and further left is better: more half-precision throughput for less power.
Specifications
Architecture
Ampere
Form Factor
SXM
Launch Year
2020
Process Node
7nm
Memory
40 GB HBM2e
Bandwidth
1,555 GB/s
TDP
400 W
Max power (Flopper estimate)
~460 W est. Flopper estimate: 400 W TDP x 1.15. The vendor publishes no maximum board power for this part.
Spec Confidence
Official
Full Specifications
| Memory | |
|---|---|
| Memory | 40 GB |
| Memory Type | HBM2e |
| Bandwidth | 1.6 TB/s |
| Interface Width | 4096-bit |
| Power & Thermal | |
| TDP | 400 W |
| Max power (Flopper estimate) | ~460 W est. |
| Enterprise Features | |
| Sparsity | Yes |
| General | |
| Form Factor | SXM |
| Architecture | Ampere |
| Process Node | 7nm |
| Launch Year | 2020 |
Datasheet & Resources
Flopper Datasheet
NVIDIA A100 SXM4 40GB specifications, generated from our database. Printable.
Vendor product page
NVIDIA documentation for the A100 SXM4 40GB
NVIDIA Developer Documentation
Technical specs, programming guides
Data Provenance
Every figure traced to a source
Primary Source
- Document
- —
- Publisher
- NVIDIA
- Published
- No verified data available
Data Quality
- Spec confidence
- Official
- Clock basis
- Boost
- Core precisions with figures
- 6 of 9
- Normalization
- All values in TFLOPS
Rent this GPU
$0.45 / GPU-hr
Lowest of 14 live listings across 9 providers· median $2.05
Median of each provider's cheapest on-demand listing, so a provider with many configurations counts once.
Price history and every provider on the pricing page. Some links are affiliate links.
Similar GPUs
Frequently Asked Questions
How many TFLOPS does the NVIDIA A100 have?
The NVIDIA A100 delivers 20 TFLOPS FP32 and 312 TFLOPS FP16 at peak. Flopper does not currently have a verified FP8 throughput figure for it.
What is the power consumption of the NVIDIA A100?
The NVIDIA A100 has a TDP (Thermal Design Power) rating of 400 watts.
How much memory does the NVIDIA A100 have?
The NVIDIA A100 is equipped with 40 GB of memory with 1,555 GB/s of memory bandwidth.
What architecture is the NVIDIA A100 based on?
The NVIDIA A100 is based on the Ampere architecture, launched in 2020.
How much does the NVIDIA A100 cost to rent?
The NVIDIA A100 rents from $0.45 per GPU-hour across 9 cloud providers, the lowest of 14 live listings Flopper tracks. The pricing page lists every provider and the price history.
When did the NVIDIA A100 come out?
The NVIDIA A100 launched in 2020 on the Ampere architecture.
Stay Updated on GPU Releases
Get notified when new GPUs are added or specifications are updated.
No spam, unsubscribe anytime.