NVIDIA later added a 72 GB version of this board, listed separately here as RTX PRO 5000 Blackwell 72GB. The two are identical in every published specification except frame buffer and MIG instance sizes. NVIDIA publishes only single-precision and a single FP4 AI TOPS headline for this card, so the FP8, FP16, BF16, TF32 and INT8 rungs are absent from this catalog rather than estimated.

NVIDIA RTX PRO 5000 Blackwell 48GB

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

Overview

The NVIDIA RTX PRO 5000 Blackwell is the mid-range professional Blackwell desktop card, with 14,080 CUDA cores, fifth-generation Tensor cores and fourth-generation RT cores, and 48 GB of GDDR7 with ECC on a 512-bit bus at 1,344 GB/s. That 512-bit interface is the tell that this is a cut-down GB202, the same die as the RTX PRO 6000, rather than a smaller chip: nothing else in the Blackwell family runs a bus that wide. At 300 W it delivers 65 TFLOPS of FP32 and 1,032 dense TFLOPS of FP4, roughly half the RTX PRO 6000 Workstation Edition for half the board power and, at launch, a good deal less than half the price. Multi-Instance GPU support lets one card be split into two isolated 24 GB instances, which matters if you are hosting several small models on one workstation. For local inference the 48 GB frame buffer is the headline number, since it holds a 70B-parameter model at 4-bit without spilling to system memory.

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

48 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 48 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 24GB, Up to 1x 48GB
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

Rent this GPU

$0.60 / GPU-hr

Lowest of 3 live listings across 2 providers· median $0.82

See all rental prices →

Price history and every provider on the pricing page. Some links are affiliate links.

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 48 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