NVIDIA names this card "NVIDIA RTX PRO 5000 72GB Blackwell", putting the capacity in the middle of the product name. It is recorded here as a memory variant of the RTX PRO 5000 Blackwell so the two sit together, which is how NVIDIA's own datasheet presents them: one two-column table where every row is shared except GPU memory and MIG instance sizes.

NVIDIA RTX PRO 5000 Blackwell 72GB

Blackwell PCIe 2025 4nm Spec confidence: Official
FP32
65
TFLOPS
VRAM
72 GB
GDDR7
Bandwidth
1.3 TB/s
memory
TDP
300 W
216.7 TFLOPS/kW
Download datasheet

Overview

The NVIDIA RTX PRO 5000 Blackwell 72GB is the large-memory version of the RTX PRO 5000, adding 24 GB of frame buffer over the 48 GB card while changing nothing else. Same 14,080 CUDA cores, same 512-bit GDDR7 bus at 1,344 GB/s, same 65 TFLOPS of FP32 and 1,032 dense TFLOPS of FP4, same 300 W board. NVIDIA reached 72 GB on a 512-bit bus by using denser GDDR7 devices, which is why bandwidth is unchanged. For local model work the capacity is the entire argument: 72 GB is enough for a 70B-parameter model at 8-bit weights, or for keeping a long context resident alongside a smaller model, on a card that still fits a 300 W workstation slot. Multi-Instance GPU splits it into two isolated 36 GB instances.

Performance

Peak theoretical throughput by precision type

PrecisionDense2:4 Sparse
FP64
No verified data available Structured sparsity is a tensor-core feature; this vector precision has no sparse form
FP32
32-bit floating point
65TFLOPS Structured sparsity is a tensor-core feature; this vector precision has no sparse form
TF32
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
BF16
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP16
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP8
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP6
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision
FP4
4-bit floating point
1,032TFLOPS 2,064TFLOPS
INT8
No verified data available The part supports 2:4 sparsity, but the vendor publishes no sparse figure for this precision

Specifications

Architecture

Blackwell

Form Factor

PCIe

Launch Year

2025

Process Node

4nm

Memory

72 GB GDDR7

Bandwidth

1,344 GB/s

TDP

300 W

Max Power

300 W

CUDA Cores

14,080

Spec Confidence

Official

Full Specifications

Compute Engine
CUDA Cores 14,080
Streaming Multiprocessors 110
Memory
VRAM 72 GB
Memory Type GDDR7
Bandwidth 1.3 TB/s
Interface Width 512-bit
Interconnect & I/O
PCIe 5.0 x16
Power & Thermal
TDP 300 W
Max Board Power 300 W
Power Connector 1x PCIe CEM5 16-pin
Cooling Active
Enterprise Features
ECC Memory Yes
MIG Support Up to 2x 36GB, Up to 1x 72GB
Sparsity Yes
Compute APIs CUDA 12.8, OpenCL 3.0, DirectCompute
Physical & Media
Card Length 266.7 mm
Width 2-slot
NVENC Engines 3
NVDEC Engines 3
General
Form Factor PCIe
Architecture Blackwell
Process Node 4nm
Launch Year 2025

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
NVIDIA
Published
2026-06-01

Data Quality

Spec confidence
Official
Clock basis
Boost
Core precisions with figures
2 of 9
Normalization
All values in TFLOPS

Compare cloud providers offering on-demand GPU instances for AI training, inference, and HPC workloads.

Browse GPU Cloud Providers

Similar GPUs

Frequently Asked Questions

How many TFLOPS does the NVIDIA RTX PRO 5000 Blackwell have?

The NVIDIA RTX PRO 5000 Blackwell delivers 65 TFLOPS FP32 at peak. Flopper does not currently have verified FP16 and FP8 throughput figures for it.

What is the power consumption of the NVIDIA RTX PRO 5000 Blackwell?

The NVIDIA RTX PRO 5000 Blackwell has a TDP (Thermal Design Power) rating of 300 watts.

How much memory does the NVIDIA RTX PRO 5000 Blackwell have?

The NVIDIA RTX PRO 5000 Blackwell is equipped with 72 GB of VRAM with 1,344 GB/s of memory bandwidth.

What architecture is the NVIDIA RTX PRO 5000 Blackwell based on?

The NVIDIA RTX PRO 5000 Blackwell is based on the Blackwell architecture, launched in 2025.

Stay Updated on GPU Releases

Get notified when new GPUs are added or specifications are updated.

Loading verification...

No spam, unsubscribe anytime.

Back to GPUs