NVIDIA GeForce RTX 2070 8GB vs NVIDIA Quadro RTX 8000 48GB

The Quadro RTX 8000 delivers 4.1x the FP16 throughput of the GeForce RTX 2070 (131 vs 32 TFLOPS dense). The Quadro RTX 8000 also carries 40 GB more memory (48 GB vs 8 GB).

GeForce RTX 2070: Turing, 2018 Quadro RTX 8000: Turing, 2018
FP16 dense lead
4.1x
Quadro RTX 8000: 131 vs 32 TFLOPS
VRAM
8 vs 48 GB
40 GB more for the Quadro RTX 8000
Bandwidth
448 GB/s vs 672 GB/s
Quadro RTX 8000 moves data faster
TDP
185 W vs 295 W
GeForce RTX 2070 draws 110 W less

Specifications

GeForce RTX 2070
Quadro RTX 8000
Architecture
TuringTuring
Launch Year
20182018
Form Factor
PCIePCIe
VRAM
8 GB48 GB
Memory Bandwidth
448 GB/s672 GB/s
TDP
185 W295 W
Process Node
12nm12nm

Performance (TFLOPS)

GeForce RTX 2070
Quadro RTX 8000
FP64
0.2 TFlops 0.5 TFlops
FP32
7.9 TFlops 16.3 TFlops
TF32
No verified data available No verified data available
BF16
No verified data available No verified data available
FP16
31.5 TFlops 130.5 TFlops
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
126.0 TFlops 261.0 TFlops

FLOPS by Precision

What actually differs

Both GPUs launched in 2018: the GeForce RTX 2070 on Turing and the Quadro RTX 8000 on Turing.

Dense throughput for the GeForce RTX 2070 against the Quadro RTX 8000: FP64 0.2 vs 0.5 TFLOPS, FP32 7.9 vs 16 TFLOPS, FP16 32 vs 131 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 8 GB against 48 GB, fed at 448 GB/s versus 672 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 185 W for the GeForce RTX 2070 and 295 W for the Quadro RTX 8000. At FP32 that works out to 0.04 against 0.06 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 GeForce RTX 2070 faster than the Quadro RTX 8000?

At FP16 precision the Quadro RTX 8000 reaches 131 TFLOPS dense against 32 TFLOPS for the GeForce RTX 2070. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the GeForce RTX 2070 or the Quadro RTX 8000?

The Quadro RTX 8000 carries 48 GB of VRAM versus 8 GB for the GeForce RTX 2070. Memory bandwidth is 448 GB/s for the GeForce RTX 2070 and 672 GB/s for the Quadro RTX 8000.

How much power do the GeForce RTX 2070 and the Quadro RTX 8000 draw?

The GeForce RTX 2070 is rated at 185 W TDP and the Quadro RTX 8000 at 295 W. On FP32 throughput per watt, the Quadro RTX 8000 is the more efficient part.

Can I rent the GeForce RTX 2070 or the Quadro RTX 8000 in the cloud?

Yes. Live cloud listings tracked by Flopper start at $0.25 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA Quadro RTX 8000 48GB

ProviderConfigurationPrice/GPU-hrChecked
Vast.ai
1× Quadro RTX 8000 48GB Community $0.25 1h ago View →
All Quadro RTX 8000 listings and price history →

Get Comparison Updates

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