NVIDIA GeForce RTX 5090 D V2 24GB vs NVIDIA RTX PRO 6000 Blackwell Server Edition

The RTX PRO 6000 Blackwell delivers 15% more FP32 throughput than the GeForce RTX 5090 D V2 (120 vs 105 TFLOPS dense). The RTX PRO 6000 Blackwell also carries 72 GB more memory (96 GB vs 24 GB).

GeForce RTX 5090 D V2: Blackwell, 2025 RTX PRO 6000 Blackwell: Blackwell, 2025
FP32 dense lead
+15%
RTX PRO 6000 Blackwell: 120 vs 105 TFLOPS
VRAM
24 vs 96 GB
72 GB more for the RTX PRO 6000 Blackwell
Bandwidth
1.3 TB/s vs 1.6 TB/s
RTX PRO 6000 Blackwell moves data faster
TDP
575 W vs 600 W
GeForce RTX 5090 D V2 draws 25 W less

Specifications

GeForce RTX 5090 D V2
RTX PRO 6000 Blackwell
Architecture
BlackwellBlackwell
Launch Year
20252025
Form Factor
PCIePCIe
VRAM
24 GB96 GB
Memory Bandwidth
1.3 TB/s1.6 TB/s
TDP
575 W600 W
Process Node
4nm4nm

Performance (TFLOPS)

GeForce RTX 5090 D V2
RTX PRO 6000 Blackwell
FP64
1.6 TFlops No verified data available
FP32
104.8 TFlops 120.0 TFlops
TF32
No verified data available234.0 TFlops
sparse not published
BF16
No verified data available The vendor publishes only the 2:4 sparse figure for this precision
1000.0 TFLOPS sparse
FP16
No verified data available The vendor publishes only the 2:4 sparse figure for this precision
1000.0 TFLOPS sparse
FP8
No verified data available The vendor publishes only the 2:4 sparse figure for this precision
2000.0 TFLOPS sparse
FP6
No verified data available No verified data available
FP4
1187.5 TFlops
2375.0 TFLOPS sparse
The vendor publishes only the 2:4 sparse figure for this precision
4000.0 TFLOPS sparse
INT8
No verified data available No verified data available

FLOPS by Precision

What actually differs

Both GPUs launched in 2025: the GeForce RTX 5090 D V2 on Blackwell and the RTX PRO 6000 Blackwell on Blackwell.

Dense throughput for the GeForce RTX 5090 D V2 against the RTX PRO 6000 Blackwell: FP32 105 vs 120 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 24 GB against 96 GB, fed at 1.3 TB/s versus 1.6 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 575 W for the GeForce RTX 5090 D V2 and 600 W for the RTX PRO 6000 Blackwell. At FP32 that works out to 0.18 against 0.20 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 5090 D V2 faster than the RTX PRO 6000 Blackwell?

At FP32 precision the RTX PRO 6000 Blackwell reaches 120 TFLOPS dense against 105 TFLOPS for the GeForce RTX 5090 D V2. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the GeForce RTX 5090 D V2 or the RTX PRO 6000 Blackwell?

The RTX PRO 6000 Blackwell carries 96 GB of VRAM versus 24 GB for the GeForce RTX 5090 D V2. Memory bandwidth is 1.3 TB/s for the GeForce RTX 5090 D V2 and 1.6 TB/s for the RTX PRO 6000 Blackwell.

How much power do the GeForce RTX 5090 D V2 and the RTX PRO 6000 Blackwell draw?

The GeForce RTX 5090 D V2 is rated at 575 W TDP and the RTX PRO 6000 Blackwell at 600 W. On FP32 throughput per watt, the RTX PRO 6000 Blackwell is the more efficient part.

Can I rent the GeForce RTX 5090 D V2 or the RTX PRO 6000 Blackwell in the cloud?

Yes. Live cloud listings tracked by Flopper start at $1.89 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA RTX PRO 6000 Blackwell Server Edition

ProviderConfigurationPrice/GPU-hrChecked
EcoHash
1× RTX PRO 6000 Blackwell Server Edition $1.89 2d ago View →
EcoHash
2× RTX PRO 6000 Blackwell Server Edition $1.89 2d ago View →
EcoHash
4× RTX PRO 6000 Blackwell Server Edition $1.89 2d ago View →
EcoHash
8× RTX PRO 6000 Blackwell Server Edition $1.89 2d ago View →
All RTX PRO 6000 Blackwell listings and price history →

Get Comparison Updates

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