A100 PCIE 80GB
Four core configurations differ by memory capacity and physical integration
SPECIFICATIONS
| Memory per accelerator | 80 GB HBM2e |
|---|---|
| Memory bandwidth | 1935 GB/s |
| Form factor | PCIe card |
| Maximum accelerator power | 300 W |
Manufacturer specifications describe the product, not the condition of an offered unit. Checked 2026-09-08
COMPUTE SPECIFICATIONS
Manufacturer peak arithmetic per accelerator. These values do not predict application throughput or latency.
| Precision | Execution | Peak rate | Sparsity | Reference |
|---|---|---|---|---|
| FP64 | Vector | 9.7 TFLOPS | Dense | Source ↗ConditionsManufacturer peak per GPU; not sustained workload performance |
| FP64 | Tensor | 19.5 TFLOPS | Dense | Source ↗ConditionsManufacturer peak per GPU; not sustained workload performance |
| FP32 | Vector | 19.5 TFLOPS | Dense | Source ↗ConditionsManufacturer peak per GPU; not sustained workload performance |
| TF32 | Tensor | 156 TFLOPS | Dense | Source ↗ConditionsManufacturer peak per GPU; not sustained workload performance |
| TF32 | Tensor | 312 TFLOPS | Structured sparse | Source ↗ConditionsManufacturer peak per GPU; not sustained workload performance |
| BF16 | Tensor | 312 TFLOPS | Dense | Source ↗ConditionsManufacturer peak per GPU; not sustained workload performance |
| BF16 | Tensor | 624 TFLOPS | Structured sparse | Source ↗ConditionsManufacturer peak per GPU; not sustained workload performance |
| FP16 | Tensor | 312 TFLOPS | Dense | Source ↗ConditionsManufacturer peak per GPU; not sustained workload performance |
| FP16 | Tensor | 624 TFLOPS | Structured sparse | Source ↗ConditionsManufacturer peak per GPU; not sustained workload performance |
| INT8 | Tensor | 624 TOPS | Dense | Source ↗ConditionsManufacturer peak per GPU; not sustained workload performance |
| INT8 | Tensor | 1248 TOPS | Structured sparse | Source ↗ConditionsManufacturer peak per GPU; not sustained workload performance |
- Peak arithmetic rates are not token throughput, latency or a guarantee of application performance
- Structured-sparse rates require eligible sparsity and supported kernels; do not compare them directly with dense rates
- The June 2021 manufacturer table explicitly spans all four memory/form-factor variants; equal listed compute rates do not imply equal memory bandwidth or power
PLATFORM AND SOFTWARE
- Specify dual-slot air cooling or single-slot liquid cooling in the request
- The cooling configuration and OEM part number must be confirmed
- Confirm driver and framework support for the intended deployment image
- Benchmark the exact precision and batch settings instead of comparing theoretical tensor figures
Manufacturer maximum accelerator rating; actual draw and supported limits depend on system
INTERCONNECT
NVLink
600 GB/s. Manufacturer aggregate bidirectional bandwidth; topology depends on platform
PCIe Gen4 x16
64 GB/s. Theoretical aggregate bidirectional interface bandwidth
MANUFACTURER SOURCES
NVIDIA A100 specifications ↗NVIDIA · Checked 2026-09-08NVIDIA A100 datasheet ↗NVIDIA · Checked 2026-09-08NVIDIA A100 four-variant datasheet, June 2021 ↗NVIDIA · Checked 2026-09-08HOW CARDINAL HELPS
Share your quantity, destination and server model, if known. We help turn those requirements into a clearly specified request.
- Help confirm the exact configuration and platform requirements
- Request supplier records for condition, unit identifiers and available testing evidence
- Clarify included accessories, delivery and proposed warranty terms before you decide
Any additional testing or guarantees must be agreed in the written offer.