Report an Error

NVIDIA Quadro RTX 4000

Graphics Processor
TU104
Cores
2304
TMUs
144
ROPs
64
Memory Size
8 GB
Memory Type
GDDR6
Bus Width
256 bit
GPU Chip
GPU
I/O
I/O
Bottom
Bottom
The Quadro RTX 4000 is an enthusiast-class professional graphics card by NVIDIA, launched in November 2018. Built on the 12 nm process, and based on the TU104 graphics processor, in its TU104-850-A1 variant, the card supports DirectX 12 Ultimate. The TU104 graphics processor is a large chip with a die area of 545 mm² and 13,600 million transistors. Unlike the fully unlocked GeForce RTX 2080 SUPER, which uses the same GPU but has all 3072 shaders enabled, NVIDIA has disabled some shading units on the Quadro RTX 4000 to reach the product's target shader count. It features 2304 shading units, 144 texture mapping units, and 64 ROPs. Also included are 288 tensor cores which help improve the speed of machine learning applications. The card also has 36 raytracing acceleration cores. NVIDIA has paired 8 GB GDDR6 memory with the Quadro RTX 4000, which are connected using a 256-bit memory interface. The GPU is operating at a frequency of 1005 MHz, which can be boosted up to 1545 MHz, memory is running at 1625 MHz (13 Gbps effective).
Being a single-slot card, the NVIDIA Quadro RTX 4000 draws power from 1x 8-pin power connector, with power draw rated at 160 W maximum. Display outputs include: 3x DisplayPort, 1x USB Type-C. Quadro RTX 4000 is connected to the rest of the system using a PCI-Express 3.0 x16 interface. The card measures 241 mm in length, 111 mm in width, and features a single-slot cooling solution. Its price at launch was 899 US Dollars.

Graphics Processor

GPU Name
TU104
GPU Variant
TU104-850-A1
Architecture
Turing
Foundry
TSMC
Process Size
12 nm
Transistors
13,600 million
Die Size
545 mm²

Graphics Card

Release Date
Nov 13th, 2018
Generation
Quadro
(Tx000)
Production
Active
Launch Price
899 USD
Bus Interface
PCIe 3.0 x16

Relative Performance

1%
GeForce 210
1%
GeForce 9400 GT
2%
Radeon HD 4550
2%
Radeon HD 5450
3%
Radeon HD 6450
3%
GeForce GT 520
4%
GeForce GT 220
5%
GeForce GT 430
5%
Radeon HD 5570
5%
Radeon HD 4670
5%
GeForce GT 440
6%
GeForce GT 240
6%
GeForce 9600 GT
7%
Radeon HD 5670
7%
GeForce GT 640
8%
GeForce 9800 GT
8%
Radeon HD 6670
8%
Radeon HD 4830
9%
Radeon HD 4770
9%
Radeon HD 4850
9%
GeForce GTS 250
10%
GeForce GTS 450
10%
Radeon HD 5750
11%
Radeon HD 7750
11%
Radeon HD 5770
12%
GeForce GTX 260
12%
Radeon HD 4870
12%
Radeon Vega 8
12%
GeForce GTX 550 Ti
12%
GeForce GTX 650
13%
Radeon HD 5830
13%
Radeon HD 6790
14%
Radeon HD 4890
14%
GeForce GTX 460
14%
Radeon RX Vega 11
14%
GeForce GT 1030
15%
GeForce GTX 275
15%
Radeon HD 7770 GHz Edition
15%
GeForce GTX 280
15%
GeForce GTX 465
16%
Radeon HD 6850
16%
GeForce GTX 285
17%
Radeon HD 5850
17%
GeForce GTX 650 Ti
17%
Radeon HD 7790
18%
Radeon RX 550
18%
GeForce GTX 470
19%
Radeon HD 6870
20%
Radeon HD 5870
21%
GeForce GTX 560 Ti
21%
Radeon HD 4870 X2
21%
GeForce GTX 750 Ti
21%
Radeon HD 6950
22%
GeForce GTX 295
22%
GeForce GTX 650 Ti Boost
22%
Radeon HD 7850
23%
GeForce GTX 480
24%
Radeon HD 6970
24%
Radeon R7 265
25%
Radeon RX 460
25%
Radeon R7 370
25%
GeForce GTX 660
25%
GeForce GTX 570
25%
Radeon RX 560
27%
GeForce GTX 950
27%
Radeon HD 7870 GHz Edition
28%
Radeon R9 270X
28%
GeForce GTX 660 Ti
28%
GeForce GTX 580
28%
GeForce GTX 1050
29%
Radeon HD 7950
29%
Radeon HD 5970
30%
GeForce GTX 760
32%
GeForce GTX 670
33%
GeForce GTX 960
34%
Radeon R9 380
34%
Radeon R9 285
34%
Radeon HD 7970
35%
GeForce GTX 680
36%
GeForce GTX 1050 Ti
37%
GeForce GTX 770
37%
Radeon HD 6990
38%
Radeon R9 280X
39%
GeForce GTX 590
39%
Radeon HD 7970 GHz Edition
43%
GeForce GTX 780
45%
GeForce GTX 1650
47%
Radeon RX 470
48%
Radeon R9 290
51%
Radeon RX 570
51%
Radeon R9 390
51%
Radeon R9 290X
52%
GeForce GTX 970
53%
GeForce GTX TITAN
54%
GeForce GTX 780 Ti
54%
Radeon R9 390X
55%
Radeon HD 7990
55%
Radeon RX 480
55%
GeForce GTX 690
57%
GeForce GTX 1060 6 GB
58%
Radeon RX 5500 OEM
58%
Radeon RX 580
59%
Radeon RX 5500 XT
59%
GeForce GTX 980
60%
GeForce GTX 1650 SUPER
60%
Radeon R9 FURY
63%
Radeon RX 590
66%
Radeon R9 295X2
67%
GeForce GTX 1660
67%
Radeon R9 FURY X
69%
GeForce GTX 980 Ti
70%
GeForce GTX TITAN X
75%
GeForce GTX 1660 SUPER
76%
GeForce GTX 1660 Ti
76%
GeForce GTX 1070
81%
Radeon RX Vega 56
86%
GeForce GTX 1070 Ti
89%
Radeon RX Vega 64
90%
GeForce RTX 2060
90%
GeForce GTX 1080
94%
Radeon RX 5700
100%
Quadro RTX 4000
101%
GeForce RTX 2060 SUPER
105%
GeForce RTX 2070
107%
Radeon RX 5700 XT
109%
Radeon VII
111%
TITAN X Pascal
115%
GeForce GTX 1080 Ti
116%
GeForce RTX 2070 SUPER
123%
GeForce RTX 2080
131%
GeForce RTX 2080 SUPER
144%
GeForce RTX 2080 Ti
191%
GeForce RTX 3080
210%
GeForce RTX 3090
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for 2080 Ti and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

Base Clock
1005 MHz
Boost Clock
1545 MHz
Memory Clock
1625 MHz
13 Gbps effective

Memory

Memory Size
8 GB
Memory Type
GDDR6
Memory Bus
256 bit
Bandwidth
416.0 GB/s

Render Config

Shading Units
2304
TMUs
144
ROPs
64
SM Count
36
Tensor Cores
288
RT Cores
36
L1 Cache
64 KB (per SM)
L2 Cache
4 MB

Theoretical Performance

Pixel Rate
98.88 GPixel/s
Texture Rate
222.5 GTexel/s
FP16 (half) performance
14.24 TFLOPS (2:1)
FP32 (float) performance
7.119 TFLOPS
FP64 (double) performance
222.5 GFLOPS (1:32)

Board Design

Slot Width
Single-slot
Length
241 mm
9.5 inches
Width
111 mm
4.4 inches
TDP
160 W
Suggested PSU
450 W
Outputs
3x DisplayPort
1x USB Type-C
Power Connectors
1x 8-pin

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.2
CUDA
7.5
Shader Model
6.5

Retail boards based on this design (1)

Name GPU Clock Boost Clock Memory Clock Other Changes
EIZO MED-XN92 1005 MHz 1545 MHz 1625 MHz