FP32 IS THE ONLY PRECISION ROW, AND THAT IS DELIBERATE. NVIDIA publishes no FP16, FP64 or INT8 rate for any GeForce or Quadro Pascal card, and the sibling GP102 parts already in this catalog (GeForce GTX 1080 Ti, TITAN Xp) carry FP32 alone for the same reason. The 5.3 TFLOPS itself does not appear on the datasheet either; NVIDIA prints it only in the QUICK SPECS panel of its Quadro desktop workstations page. REFUSED: base and boost clocks, which NVIDIA publishes for neither Pascal Quadro in any datasheet revision, product page or press release; memory_clock_gbps, since NVIDIA prints "Up to 243 GB/s" and a 256-bit bus but no data rate, and the arithmetic does not land on a round GDDR5 speed; ECC, transistor count and die size, unstated for this SKU. The 16 nm process node and the Pascal architecture link come from the GP104 die-level figures in NVIDIA's GeForce GTX 1080 whitepaper, which cover this die.

NVIDIA Quadro P4000 8GB

Pascal PCIe 2017 16nm Spec confidence: Official
FP32
5.3
TFLOPS
Memory
8 GB
GDDR5
Bandwidth
243 GB/s
memory
TDP
105 W
50.5 FP32 dense TFLOPS/kW of TDP
Download datasheet

Overview

The Quadro P4000 is the single-slot, 105 W Pascal workstation card, and it is in this database because it is still widely rented as a cheap CUDA endpoint rather than because anyone trains on it. It pairs 1,792 CUDA cores with 8 GB of GDDR5 on a 256-bit bus at 243 GB/s, which NVIDIA rates at 5.3 TFLOPS FP32, and it fits in a single slot drawing under the 75 W the PCIe connector supplies plus one six-pin cable. What it does not have is any of the machinery the later architectures are sold on: no Tensor Cores, no structured sparsity, and no published half-precision or double-precision rate of any kind, because Pascal's consumer and workstation dies run FP16 at a fraction of the shader rate and NVIDIA never quoted it. For inference that means everything runs in FP32, at 5.3 TFLOPS, and the 8 GB frame buffer is the real constraint.

Performance

Peak theoretical throughput by precision type

PrecisionPeak
FP64
No verified data available
FP32
32-bit floating point
5.3TFLOPS
TF32
No verified data available
BF16
No verified data available
FP16
No verified data available
FP8
No verified data available
FP6
No verified data available
FP4
No verified data available
INT8
No verified data available

Every figure here is dense. The vendor documents no structured (2:4) sparsity mode for this part, so there is no second number to quote.

Specifications

Architecture

Pascal

Form Factor

PCIe

Launch Year

2017

Process Node

16nm

Memory

8 GB GDDR5

Bandwidth

243 GB/s

TDP

105 W

Max power

105 W

CUDA Cores

1,792

Spec Confidence

Official

Full Specifications

Compute Engine
CUDA Cores 1,792
Streaming Multiprocessors 14
Memory
Memory 8 GB
Memory Type GDDR5
Bandwidth 243 GB/s
Interface Width 256-bit
Interconnect & I/O
PCIe 3.0 x16
Power & Thermal
TDP 105 W
Max power 105 W
Cooling Active
Enterprise Features
Sparsity No
Compute APIs CUDA, DirectCompute, OpenCL
Physical & Media
Width 1-slot
General
Form Factor PCIe
Architecture Pascal
Process Node 16nm
Launch Year 2017

Datasheet & Resources

Data Provenance

Every figure traced to a source

Primary Source

Publisher
NVIDIA
Published
No verified data available

Data Quality

Spec confidence
Official
Clock basis
Boost
Core precisions with figures
1 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

NVIDIA Titan Xp 12GB

PCIe · 2017
FP32: 12 TFLOPS
Compare vs Titan Xp

NVIDIA Tesla P40 24GB

PCIe · 2016
FP32: 12 TFLOPS
Compare vs Tesla P40

NVIDIA P100 SXM2 16GB

SXM · 2016
FP32: 11 TFLOPS
Compare vs P100

NVIDIA P100 PCIe 16GB

PCIe · 2016
FP32: 9.3 TFLOPS
Compare vs P100

Frequently Asked Questions

How many TFLOPS does the NVIDIA Quadro P4000 have?

The NVIDIA Quadro P4000 delivers 5.3 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 Quadro P4000?

The NVIDIA Quadro P4000 has a TDP (Thermal Design Power) rating of 105 watts.

How much memory does the NVIDIA Quadro P4000 have?

The NVIDIA Quadro P4000 is equipped with 8 GB of memory with 243 GB/s of memory bandwidth.

What architecture is the NVIDIA Quadro P4000 based on?

The NVIDIA Quadro P4000 is based on the Pascal architecture, launched in 2017.

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