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
| Model | Memory | Memory type | Bandwidth | Platform |
|---|---|---|---|---|
| NVIDIA RTX PRO 6000 Blackwell Max-Q Workstation Edition | 96 GB | GDDR7 ECC | 1,792 GB/s | 3,511 TOPS |
| NVIDIA RTX PRO 6000 Blackwell Workstation Edition | 96 GB | GDDR7 ECC | 1,792 GB/s | 4,000 TOPS |
| AMD Radeon PRO W7900 | 48 GB | GDDR6 ECC | 864 GB/s | - |
| NVIDIA RTX 6000 Ada Generation | 48 GB | GDDR6 ECC | 960 GB/s | 1,457 TOPS |
| NVIDIA RTX PRO 5000 Blackwell | 48 GB | GDDR7 ECC | 1,344 GB/s | 2,064 TOPS |
| AMD Radeon AI PRO R9700 | 32 GB | GDDR6 (ECC on Linux only) | 640 GB/s | - |