NVIDIA A16 16GB vs NVIDIA RTX A6000 48GB

The RTX A6000 delivers 8.6x the FP16 throughput of the A16 (155 vs 18 TFLOPS dense). The RTX A6000 also carries 32 GB more memory (48 GB vs 16 GB).

A16: Ampere, 2021 RTX A6000: Ampere, 2020
FP16 dense lead
8.6x
RTX A6000: 155 vs 18 TFLOPS
Memory
16 vs 48 GB
32 GB more for the RTX A6000
Bandwidth
200 GB/s vs 768 GB/s
RTX A6000 moves data faster

Specifications

A16
RTX A6000
Architecture
AmpereAmpere
Launch Year
20212020
Form Factor
PCIePCIe
Memory
16 GB48 GB
Memory Bandwidth
200 GB/s768 GB/s
TDP
300 W
Process Node
8nm

Performance (TFLOPS)

A16
RTX A6000
FP64
No verified data available0.6 TFlops
FP32
4.5 TFlops 38.7 TFlops
TF32
9.0 TFlops
18.0 TFLOPS sparse
77.4 TFlops
154.8 TFLOPS sparse
BF16
No verified data available154.8 TFlops
309.6 TFLOPS sparse
FP16
17.9 TFlops
35.9 TFLOPS sparse
154.8 TFlops
309.6 TFLOPS sparse
FP8
No verified data available No verified data available
FP6
No verified data available No verified data available
FP4
No verified data available No verified data available
INT8
35.9 TFlops
71.8 TOPS sparse
309.7 TFlops
619.4 TOPS sparse

FLOPS by Precision

What actually differs

The A16 is the newer part: Ampere, launched in 2021, against the RTX A6000's Ampere from 2020. Newer architectures typically add lower-precision formats and better throughput per watt, so check the precision rows your workload actually uses.

Dense throughput for the A16 against the RTX A6000: FP32 4.5 vs 39 TFLOPS, FP16 18 vs 155 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 16 GB against 48 GB, fed at 200 GB/s versus 768 GB/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.

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 A16 faster than the RTX A6000?

At FP16 precision the RTX A6000 reaches 155 TFLOPS dense against 18 TFLOPS for the A16. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the A16 or the RTX A6000?

The RTX A6000 carries 48 GB of memory versus 16 GB for the A16. Memory bandwidth is 200 GB/s for the A16 and 768 GB/s for the RTX A6000.

Can I rent the A16 or the RTX A6000 in the cloud?

Yes. Live cloud listings tracked by Flopper start at $0.30 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA RTX A6000 48GB

ProviderConfigurationPrice/GPU-hrChecked
DataCrunch
1× RTX A6000 48GB Spot $0.30 5h ago View →
RunPod
1× RTX A6000 48GB Community $0.33 5h ago View →
Hyperstack
1× RTX A6000 48GB Spot $0.40 5h ago View →
Vast.ai
6× RTX A6000 48GB Community $0.40 5h ago View →
Hyperstack
1× RTX A6000 48GB $0.50 5h ago View →
RunPod
1× RTX A6000 48GB $0.53 5h ago View →
Massed Compute
2× RTX A6000 48GB $0.57 5h ago View →
DataCrunch
1× RTX A6000 48GB $0.61 5h ago View →
AceCloud
1× RTX A6000 48GB $0.93 5h ago View →
Lambda Labs
1× RTX A6000 48GB $1.09 5h ago View →
Lambda Labs
4× RTX A6000 48GB $1.09 5h ago View →
Paperspace
1× RTX A6000 48GB $1.93 5h ago View →
All RTX A6000 listings and price history →

Get Comparison Updates

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