NVIDIA RTX 4000 SFF Ada 20GB vs NVIDIA RTX 6000 Ada 48GB

The RTX 6000 Ada delivers 4.7x the FP8 throughput of the RTX 4000 SFF Ada (729 vs 153 TFLOPS dense). The RTX 6000 Ada also carries 28 GB more memory (48 GB vs 20 GB).

RTX 4000 SFF Ada: Ada Lovelace, 2023 RTX 6000 Ada: Ada Lovelace, 2023
FP8 dense lead
4.7x
RTX 6000 Ada: 729 vs 153 TFLOPS
VRAM
20 vs 48 GB
28 GB more for the RTX 6000 Ada
Bandwidth
280 GB/s vs 960 GB/s
RTX 6000 Ada moves data faster
TDP
70 W vs 300 W
RTX 4000 SFF Ada draws 230 W less

Specifications

RTX 4000 SFF Ada
RTX 6000 Ada
Architecture
Ada LovelaceAda Lovelace
Launch Year
20232023
Form Factor
PCIePCIe
VRAM
20 GB48 GB
Memory Bandwidth
280 GB/s960 GB/s
TDP
70 W300 W
Process Node
4nm4nm

Performance (TFLOPS)

RTX 4000 SFF Ada
RTX 6000 Ada
FP64
0.3 TFlops No verified data available
FP32
19.2 TFlops 91.1 TFlops
TF32
No verified data available No verified data available
BF16
No verified data available No verified data available
FP16
No verified data available No verified data available
FP8
153.4 TFlops
306.8 TFLOPS sparse
728.5 TFlops
1457.0 TFLOPS sparse
FP6
No verified data available No verified data available
FP4
No verified data available No verified data available
INT8
No verified data available No verified data available

FLOPS by Precision

What actually differs

Both GPUs launched in 2023: the RTX 4000 SFF Ada on Ada Lovelace and the RTX 6000 Ada on Ada Lovelace.

Dense throughput for the RTX 4000 SFF Ada against the RTX 6000 Ada: FP32 19 vs 91 TFLOPS, FP8 153 vs 729 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 20 GB against 48 GB, fed at 280 GB/s versus 960 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.

Power budgets are 70 W for the RTX 4000 SFF Ada and 300 W for the RTX 6000 Ada. At FP32 that works out to 0.27 against 0.30 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 RTX 4000 SFF Ada faster than the RTX 6000 Ada?

At FP8 precision the RTX 6000 Ada reaches 729 TFLOPS dense against 153 TFLOPS for the RTX 4000 SFF Ada. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the RTX 4000 SFF Ada or the RTX 6000 Ada?

The RTX 6000 Ada carries 48 GB of VRAM versus 20 GB for the RTX 4000 SFF Ada. Memory bandwidth is 280 GB/s for the RTX 4000 SFF Ada and 960 GB/s for the RTX 6000 Ada.

How much power do the RTX 4000 SFF Ada and the RTX 6000 Ada draw?

The RTX 4000 SFF Ada is rated at 70 W TDP and the RTX 6000 Ada at 300 W. On FP32 throughput per watt, the RTX 6000 Ada is the more efficient part.

Can I rent the RTX 4000 SFF Ada or the RTX 6000 Ada in the cloud?

Yes. Live cloud listings tracked by Flopper start at $0.18 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA RTX 4000 SFF Ada 20GB

ProviderConfigurationPrice/GPU-hrChecked
RunPod
1× RTX 4000 SFF Ada 20GB Community $0.18 1h ago View →
RunPod
1× RTX 4000 SFF Ada 20GB $0.44 1h ago View →
All RTX 4000 SFF Ada listings and price history →

NVIDIA RTX 6000 Ada 48GB

ProviderConfigurationPrice/GPU-hrChecked
Vast.ai
4× RTX 6000 Ada 48GB Community $0.49 1h ago View →
DataCrunch
1× RTX 6000 Ada 48GB Spot $0.52 1h ago View →
RunPod
1× RTX 6000 Ada 48GB Community $0.74 1h ago View →
RunPod
1× RTX 6000 Ada 48GB $0.84 1h ago View →
Massed Compute
4× RTX 6000 Ada 48GB $0.97 1h ago View →
DataCrunch
1× RTX 6000 Ada 48GB $1.04 1h ago View →
AceCloud
1× RTX 6000 Ada 48GB $1.14 1h ago View →
DigitalOcean
1× RTX 6000 Ada 48GB $1.57 1h ago View →
All RTX 6000 Ada listings and price history →

Get Comparison Updates

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