Skip to content

Workstation GPUs

NVIDIA RTX PRO 6000 Blackwell Server Edition

Memory

96 GB

Bandwidth

1,597 GB/s

FP16

1,000 TFLOPS

FP8

2,000 TFLOPS

Maker
NVIDIA
Model
RTX PRO 6000 Blackwell Server Edition
Type
Workstation GPUs
Memory
96 GB
Memory type
GDDR7 ECC
Bandwidth
1,597 GB/s
FP16
1,000 TFLOPS
FP8
2,000 TFLOPS
FP4
4,000 TFLOPS
Power
600 W
Form factor
PCIe dual-slot FHFL, passive (air-cooled); single-slot FHXL liquid-cooled option
Interface
PCIe 5.0 x16
Released
2025

Notes on these figures

CAUTION: NVIDIA lists FP4 4 PFLOPS, FP8 2 PFLOPS, FP16/BF16 1 PFLOP tensor with no dense/sparse footnote; FP4 matches the Workstation Edition 4000 AI TOPS that NVIDIA footnotes as sparse, so these are likely sparse figures. Power up to 600 W, configurable (450/600 W cap per product spec). FP32 120 TFLOPS. No AI TOPS label published. Datasheet: https://dam-cdn.nvd.orangelogic.com/AssetLink/707m1632ypg4du1fj3ci1jo3h4w1k78j.pdf (via resources.nvidia.com/en-us-rtx-pro-6000). Announced 2025-03-18. No official MSRP.

Source: the maker's published specifications at nvidia.com. A missing figure means the maker does not publish it. Confirm current specifications with the maker or a dealer before you buy.

Comparable workstation gpus

ModelMemoryMemory typeBandwidthPlatform
NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition96 GBGDDR7 ECC1,792 GB/s3,511 TOPS
NVIDIA RTX PRO 6000 Blackwell Workstation Edition96 GBGDDR7 ECC1,792 GB/s4,000 TOPS
AMD Radeon PRO W790048 GBGDDR6 ECC864 GB/s-
NVIDIA RTX 6000 Ada Generation48 GBGDDR6 ECC960 GB/s1,457 TOPS
NVIDIA RTX PRO 5000 Blackwell48 GBGDDR7 ECC1,344 GB/s2,064 TOPS
AMD Radeon AI PRO R970032 GBGDDR6 (ECC on Linux only)640 GB/s-