NVIDIA GB200 Grace Blackwell Superchip 372GB vs NVIDIA RTX PRO 6000D 84GB
The GB200 delivers 65% more FP32 throughput than the RTX PRO 6000D (160 vs 97 TFLOPS dense). The GB200 also carries 288 GB more memory (372 GB vs 84 GB).
NVIDIA GB200 Grace Blackwell Superchip 372GB
Full specs →NVIDIA RTX PRO 6000D 84GB
Full specs →Specifications
Performance (TFLOPS)
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 160 vs 97 TFLOPS. Sparse figures, where the vendor publishes them, appear under each dense number in the performance table.
Memory is 372 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 GB200 reaches 160 TFLOPS dense against 97 TFLOPS for the RTX PRO 6000D. 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 372 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
Get Comparison Updates
New GPUs added weekly. Be the first to see how they compare.