NVIDIA A100 Tensor Core GPU (40GB)

Buying advice

The NVIDIA A100 is a premier enterprise accelerator featuring 40GB of high-speed memory, specifically engineered to power large-scale AI training and complex scientific simulations. It represents a top-tier solution for professional data centers focused on high-performance computing and running advanced language models.

Specifications

LAUNCH

Released: 2020

GAMING PERFORMANCE

Gaming Performance Index (GPI): -PS5 reference: 2024 = 100 · Input years: unknown · No applicable generic or configuration GPI estimate is established.

GRAPHICS BENCHMARKS

3DMark Score: -

MEMORY & STORAGE

Graphics Memory: 40 GB HBM2
Memory Bandwidth: 1,555 GB/sVendor bandwidth, both40GB SXM and40GB PCIe columns
Bus Width: 5,120 bit

ARCHITECTURE & COMPUTE

* FP32 describes floating-point throughput, not measured gaming performance. Architecture, clock and method differences affect comparison.

Architecture: Ampere
Process: 7 nm
Platform: Desktop
FP32 TFLOPS*: Conditions unconfirmed19.5
Test conditions & details
Test: FP32
Score unit: TFLOPS
Version not recorded
Recorded test: Unknown
Bars align retained values of the same metric and unit. Test conditions may be unconfirmed. The endpoint is a display scale, not a test maximum, comparable device measurement, game FPS ratio or winner.
FP16 (AI) TFLOPS: -
Resolution & frame-rate reference: 1440p / 60 fps

POWER & BATTERY

Power: PCIe: 250 W · SXM: 400 W

OTHER SPECIFICATIONS

Manufacturer: NVIDIA