NVIDIA A800 PCIe 80GB vs NVIDIA GeForce RTX 3090 Ti 24GB

The A800 delivers 7.8x the FP16 throughput of the GeForce RTX 3090 Ti (312 vs 40 TFLOPS dense). The A800 also carries 56 GB more memory (80 GB vs 24 GB).

A800: Ampere, 2022 GeForce RTX 3090 Ti: Ampere, 2022
FP16 dense lead
7.8x
A800: 312 vs 40 TFLOPS
VRAM
80 vs 24 GB
56 GB more for the A800
Bandwidth
1.9 TB/s vs 1.0 TB/s
A800 moves data faster
TDP
300 W vs 450 W
A800 draws 150 W less

Specifications

A800
GeForce RTX 3090 Ti
Architecture
AmpereAmpere
Launch Year
20222022
Form Factor
PCIePCIe
VRAM
80 GB24 GB
Memory Bandwidth
1.9 TB/s1.0 TB/s
TDP
300 W450 W
Process Node
7nm8nm

Performance (TFLOPS)

A800
GeForce RTX 3090 Ti
FP64
9.7 TFlops 0.6 TFlops
FP32
19.5 TFlops 40.0 TFlops
FP16
312.0 TFlops
sparse not published
40.0 TFlops
sparse not published
BF16
312.0 TFlops
sparse not published
40.0 TFlops
sparse not published
INT8
624.0 TFlops
sparse not published
80.0 TFlops
sparse not published

FLOPS by Precision

What actually differs

Both GPUs launched in 2022: the A800 on Ampere and the GeForce RTX 3090 Ti on Ampere.

Dense throughput for the A800 against the GeForce RTX 3090 Ti: FP64 9.7 vs 0.6 TFLOPS, FP32 20 vs 40 TFLOPS, FP16 312 vs 40 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 80 GB against 24 GB, fed at 1.9 TB/s versus 1.0 TB/s. More memory per GPU means larger models fit before you have to shard across cards, which often matters more than raw TFLOPS for inference.

Power budgets are 300 W for the A800 and 450 W for the GeForce RTX 3090 Ti. At FP32 that works out to 0.07 against 0.09 TFLOPS per watt.

For LLM training and inference, weight the FP8 and FP16 rows and memory capacity most heavily. For scientific and HPC workloads, the FP64 row is the one to read.

Frequently asked questions

Is the A800 faster than the GeForce RTX 3090 Ti?

At FP16 precision the A800 reaches 312 TFLOPS dense against 40 TFLOPS for the GeForce RTX 3090 Ti. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the A800 or the GeForce RTX 3090 Ti?

The A800 carries 80 GB of VRAM versus 24 GB for the GeForce RTX 3090 Ti. Memory bandwidth is 1.9 TB/s for the A800 and 1.0 TB/s for the GeForce RTX 3090 Ti.

How much power do the A800 and the GeForce RTX 3090 Ti draw?

The A800 is rated at 300 W TDP and the GeForce RTX 3090 Ti at 450 W. On FP32 throughput per watt, the GeForce RTX 3090 Ti is the more efficient part.

Can I rent the A800 or the GeForce RTX 3090 Ti in the cloud?

Yes. Live cloud listings tracked by Flopper start at $0.27 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA GeForce RTX 3090 Ti 24GB

ProviderConfigurationPrice/GPU-hrChecked
RunPod
1× GeForce RTX 3090 Ti 24GB Community $0.27 5h ago View →
RunPod
1× GeForce RTX 3090 Ti 24GB $0.46 5h ago View →
All GeForce RTX 3090 Ti listings and price history →

Get Comparison Updates

New GPUs added weekly. Be the first to see how they compare.