NVIDIA A10G 24GB vs NVIDIA GeForce RTX 3090 Ti 24GB

The A10G delivers 75% more FP16 throughput than the GeForce RTX 3090 Ti (70 vs 40 TFLOPS dense).

A10G: Ampere, 2022 GeForce RTX 3090 Ti: Ampere, 2022
FP16 dense lead
+75%
A10G: 70 vs 40 TFLOPS
VRAM
24 vs 24 GB
Same capacity
Bandwidth
600 GB/s vs 1.0 TB/s
GeForce RTX 3090 Ti moves data faster
TDP
300 W vs 450 W
A10G draws 150 W less

Specifications

A10G
GeForce RTX 3090 Ti
Architecture
AmpereAmpere
Launch Year
20222022
Form Factor
PCIePCIe
VRAM
24 GB24 GB
Memory Bandwidth
600 GB/s1.0 TB/s
TDP
300 W450 W
Process Node
8nm8nm

Performance (TFLOPS)

A10G
GeForce RTX 3090 Ti
FP64
0.6 TFlops
FP32
35.0 TFlops 40.0 TFlops
FP16
70.0 TFlops
sparse not published
40.0 TFlops
sparse not published
BF16
70.0 TFlops
sparse not published
40.0 TFlops
sparse not published
INT8
140.0 TFlops
sparse not published
80.0 TFlops
sparse not published

FLOPS by Precision

What actually differs

Both GPUs launched in 2022: the A10G on Ampere and the GeForce RTX 3090 Ti on Ampere.

Dense throughput for the A10G against the GeForce RTX 3090 Ti: FP32 35 vs 40 TFLOPS, FP16 70 vs 40 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 24 GB against 24 GB, fed at 600 GB/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 A10G and 450 W for the GeForce RTX 3090 Ti. At FP32 that works out to 0.12 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 A10G faster than the GeForce RTX 3090 Ti?

At FP16 precision the A10G reaches 70 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 A10G or the GeForce RTX 3090 Ti?

Both GPUs carry 24 GB of VRAM. Memory bandwidth is 600 GB/s for the A10G and 1.0 TB/s for the GeForce RTX 3090 Ti.

How much power do the A10G and the GeForce RTX 3090 Ti draw?

The A10G is rated at 300 W TDP and the GeForce RTX 3090 Ti at 450 W. On FP32 throughput per watt, the A10G is the more efficient part.

Can I rent the A10G 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 just now View →
RunPod
1× GeForce RTX 3090 Ti 24GB $0.46 just now 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.