Skip to content
HardwareLadder
AI GPU ladder

NVIDIAAI GPU · PCIe

RTX PRO 6000 Server

NVIDIA RTX PRO 6000 Server is a Blackwell data-center accelerator with 96 GB GDDR7 and 1.597 TB/s of memory bandwidth.

Ladder rank
#13
AI index (H100 SXM = 100)
49.3
Series
Blackwell

Specifications

Dense throughput, no sparsity
Architecture Blackwell
Form factor PCIe
Process TSMC 4NP
FP16 / BF16 tensor (dense) 503.8 TFLOPS
FP8 tensor (dense) 1,007.6 TFLOPS
FP4 tensor (dense) 2,015.2 TFLOPS
Memory 96 GB GDDR7
Memory bandwidth 1.597 TB/s
Power Up to 600 W
Launch Mar 2025

AI index

Tensor × bandwidth

100 × √((503.8 ÷ 989.4) × (1.597 ÷ 3.35)) = 49.3

The AI index is the geometric mean of dense 16-bit tensor throughput and memory bandwidth, each relative to the H100 SXM. It is a spec-sheet comparison, not a measured benchmark.

Sources

2 references