NVIDIA GB200 NVL72 GPU 186GB vs NVIDIA RTX PRO 6000D 84GB

The RTX PRO 6000D delivers 21% more FP32 throughput than the GB200 (97 vs 80 TFLOPS dense). The GB200 counters with 102 GB more memory (186 GB vs 84 GB).

GB200: Blackwell, 2024 RTX PRO 6000D: Blackwell, 2025
FP32 dense lead
+21%
RTX PRO 6000D: 97 vs 80 TFLOPS
Memory
186 vs 84 GB
102 GB more for the GB200
See rental pricing from $1.07/hr Download comparison sheet

Share this page

NVIDIA GB200 NVL72 GPU 186GB vs NVIDIA RTX PRO 6000D 84GB

A post with this link shows the card on the Image tab as its preview.

Printable version →

Specifications

GB200
RTX PRO 6000D
Architecture
BlackwellBlackwell
Launch Year
20242025
Form Factor
SXMPCIe
Memory
186 GB84 GB
Memory Bandwidth
8.0 TB/s—
TDP
——
Process Node
4nm—

Performance (TFLOPS)

GB200
RTX PRO 6000D
FP64
40 TFLOPS No verified data available
FP32
80 TFLOPS 97 TFLOPS
TF32
1,250 TFLOPS
2,500 TFLOPS sparse
No verified data available
BF16
2,500 TFLOPS
5,000 TFLOPS sparse
No verified data available
FP16
2,500 TFLOPS
5,000 TFLOPS sparse
No verified data available
FP8
5,000 TFLOPS
10,000 TFLOPS sparse
No verified data available
FP6
5,000 TFLOPS
10,000 TFLOPS sparse
No verified data available
FP4
10,000 TFLOPS
20,000 TFLOPS sparse
No verified data available
INT8
5,000 TOPS
10,000 TOPS sparse
No verified data available

FLOPS by Precision

What actually differs

The RTX PRO 6000D is the newer part: Blackwell, launched in 2025, against the GB200's Blackwell from 2024. 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 GB200 against the RTX PRO 6000D: FP32 80 vs 97 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.

Memory is 186 GB against 84 GB. 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 GB200 faster than the RTX PRO 6000D?

At FP32 precision the RTX PRO 6000D reaches 97 TFLOPS dense against 80 TFLOPS for the GB200. The performance table on this page lists every published precision for both GPUs.

Which has more memory, the GB200 or the RTX PRO 6000D?

The GB200 carries 186 GB of memory versus 84 GB for the RTX PRO 6000D.

Can I rent the GB200 or the RTX PRO 6000D in the cloud?

Yes. Live cloud listings tracked by Flopper start at $1.07 per GPU hour. The rental pricing section on this page lists current providers and rates for both GPUs.

Where to Rent

NVIDIA GB200 NVL72 GPU 186GB

ProviderConfigurationPrice/GPU-hrChecked
4× GB200 NVL72 GPU $10.50 3h ago View →
1× GB200 NVL72 GPU $16.00 3h ago View →
All GB200 listings and price history →

NVIDIA RTX PRO 6000D 84GB

ProviderConfigurationPrice/GPU-hrChecked
1× RTX PRO 6000D 84GB Community $1.07 3h ago View →
All RTX PRO 6000D listings and price history →

Get Comparison Updates

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

© 2026 Flopper.io - Compare the GPUs Powering AI