Quadro P520 vs Tesla T4
Aggregate performance score
We've compared Tesla T4 with Quadro P520, including specs and performance data.
T4 outperforms P520 by a whopping 391% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 264 | 686 |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 26.05 | 20.62 |
| Architecture | Turing (2018−2022) | Pascal (2016−2021) |
| GPU code name | TU104 | GP108 |
| Market segment | Workstation | Mobile workstation |
| Release date | 13 September 2018 (7 years ago) | 23 May 2019 (6 years ago) |
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 2560 | 384 |
| Core clock speed | 585 MHz | 1303 MHz |
| Boost clock speed | 1590 MHz | 1493 MHz |
| Number of transistors | 13,600 million | 1,800 million |
| Manufacturing process technology | 12 nm | 14 nm |
| Power consumption (TDP) | 70 Watt | 18 Watt |
| Texture fill rate | 254.4 | 35.83 |
| Floating-point processing power | 8.141 TFLOPS | 1.147 TFLOPS |
| ROPs | 64 | 16 |
| TMUs | 160 | 24 |
| Tensor Cores | 320 | no data |
| Ray Tracing Cores | 40 | no data |
| L1 Cache | 2.5 MB | 144 KB |
| L2 Cache | 4 MB | 512 KB |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Laptop size | no data | large |
| Interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Length | 168 mm | no data |
| Width | 1-slot | no data |
| Supplementary power connectors | None | None |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | GDDR6 | GDDR5 |
| Maximum RAM amount | 16 GB | 2 GB |
| Memory bus width | 256 Bit | 64 Bit |
| Memory clock speed | 1250 MHz | 1502 MHz |
| Memory bandwidth | 320.0 GB/s | 48.06 GB/s |
| Shared memory | - | - |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | No outputs | No outputs |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_1) | 12 (12_1) |
| Shader Model | 6.5 | 6.4 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 1.2 |
| Vulkan | 1.2.131 | 1.2.131 |
| CUDA | 7.5 | 6.1 |
| DLSS | + | - |
Synthetic benchmarks
Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.
Combined synthetic benchmark score
This is our combined benchmark score.
Passmark
This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.
GeekBench 5 OpenCL
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses OpenCL API by Khronos Group.
GeekBench 5 CUDA
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses CUDA API by NVIDIA.
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
Average FPS across all PC games
Here are the average frames per second in a large set of popular games across different resolutions:
| Full HD | 100−110
+376%
| 21
−376%
|
| 4K | 95−100
+375%
| 20
−375%
|
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 21−24
+0%
|
21−24
+0%
|
| Cyberpunk 2077 | 10−11
+0%
|
10−11
+0%
|
| Resident Evil 4 Remake | 8−9
+0%
|
8−9
+0%
|
Full HD
Medium
| Battlefield 5 | 20−22
+0%
|
20−22
+0%
|
| Counter-Strike 2 | 21−24
+0%
|
21−24
+0%
|
| Cyberpunk 2077 | 10−11
+0%
|
10−11
+0%
|
| Far Cry 5 | 20
+0%
|
20
+0%
|
| Fortnite | 27−30
+0%
|
27−30
+0%
|
| Forza Horizon 4 | 21−24
+0%
|
21−24
+0%
|
| Forza Horizon 5 | 14−16
+0%
|
14−16
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18−20
+0%
|
18−20
+0%
|
| Valorant | 60−65
+0%
|
60−65
+0%
|
Full HD
High
| Battlefield 5 | 20−22
+0%
|
20−22
+0%
|
| Counter-Strike 2 | 21−24
+0%
|
21−24
+0%
|
| Counter-Strike: Global Offensive | 80−85
+0%
|
80−85
+0%
|
| Cyberpunk 2077 | 10−11
+0%
|
10−11
+0%
|
| Dota 2 | 60
+0%
|
60
+0%
|
| Far Cry 5 | 18
+0%
|
18
+0%
|
| Fortnite | 27−30
+0%
|
27−30
+0%
|
| Forza Horizon 4 | 21−24
+0%
|
21−24
+0%
|
| Forza Horizon 5 | 14−16
+0%
|
14−16
+0%
|
| Grand Theft Auto V | 16−18
+0%
|
16−18
+0%
|
| Metro Exodus | 6
+0%
|
6
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18−20
+0%
|
18−20
+0%
|
| The Witcher 3: Wild Hunt | 19
+0%
|
19
+0%
|
| Valorant | 60−65
+0%
|
60−65
+0%
|
Full HD
Ultra
| Battlefield 5 | 20−22
+0%
|
20−22
+0%
|
| Cyberpunk 2077 | 10−11
+0%
|
10−11
+0%
|
| Dota 2 | 54
+0%
|
54
+0%
|
| Far Cry 5 | 16
+0%
|
16
+0%
|
| Forza Horizon 4 | 21−24
+0%
|
21−24
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 18−20
+0%
|
18−20
+0%
|
| The Witcher 3: Wild Hunt | 11
+0%
|
11
+0%
|
| Valorant | 60−65
+0%
|
60−65
+0%
|
Full HD
Epic
| Fortnite | 27−30
+0%
|
27−30
+0%
|
1440p
High
| Counter-Strike 2 | 10−11
+0%
|
10−11
+0%
|
| Counter-Strike: Global Offensive | 35−40
+0%
|
35−40
+0%
|
| Grand Theft Auto V | 4−5
+0%
|
4−5
+0%
|
| Metro Exodus | 4−5
+0%
|
4−5
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 35−40
+0%
|
35−40
+0%
|
| Valorant | 50−55
+0%
|
50−55
+0%
|
1440p
Ultra
| Battlefield 5 | 4−5
+0%
|
4−5
+0%
|
| Cyberpunk 2077 | 3−4
+0%
|
3−4
+0%
|
| Far Cry 5 | 9−10
+0%
|
9−10
+0%
|
| Forza Horizon 4 | 12−14
+0%
|
12−14
+0%
|
| The Witcher 3: Wild Hunt | 7−8
+0%
|
7−8
+0%
|
1440p
Epic
| Fortnite | 10−11
+0%
|
10−11
+0%
|
4K
High
| Grand Theft Auto V | 16−18
+0%
|
16−18
+0%
|
| The Witcher 3: Wild Hunt | 1−2
+0%
|
1−2
+0%
|
| Valorant | 24−27
+0%
|
24−27
+0%
|
4K
Ultra
| Battlefield 5 | 2−3
+0%
|
2−3
+0%
|
| Cyberpunk 2077 | 1−2
+0%
|
1−2
+0%
|
| Dota 2 | 23
+0%
|
23
+0%
|
| Far Cry 5 | 4−5
+0%
|
4−5
+0%
|
| Forza Horizon 4 | 7−8
+0%
|
7−8
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 5−6
+0%
|
5−6
+0%
|
4K
Epic
| Fortnite | 5−6
+0%
|
5−6
+0%
|
This is how Tesla T4 and Quadro P520 compete in popular games:
- Tesla T4 is 376% faster in 1080p
- Tesla T4 is 375% faster in 4K
All in all, in popular games:
- there's a draw in 57 tests (100%)
Pros & cons summary
| Performance score | 23.68 | 4.82 |
| Recency | 13 September 2018 | 23 May 2019 |
| Maximum RAM amount | 16 GB | 2 GB |
| Chip lithography | 12 nm | 14 nm |
| Power consumption (TDP) | 70 Watt | 18 Watt |
Tesla T4 has a 391% higher aggregate performance score, a 700% higher maximum VRAM amount, and a 17% more advanced lithography process.
Quadro P520, on the other hand, has an age advantage of 8 months, and 289% lower power consumption.
The Tesla T4 is our recommended choice as it beats the Quadro P520 in performance tests.
Be aware that Tesla T4 is a workstation graphics card while Quadro P520 is a mobile workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
