NVIDIA GeForce RTX 2080 SUPER

NVIDIA GeForce RTX 2080 SUPER

NVIDIA GeForce RTX 2080 SUPER in 2025: Is it Worth Getting the Legendary Graphics Card?

Review for Gamers and Professionals


Introduction

Launched in 2019, the NVIDIA GeForce RTX 2080 SUPER has become a symbol of the transition to an era of realistic graphics with ray tracing support. Six years later, this model remains popular in the secondary market, and new units can still be found for sale at reduced prices (around $300–400). But how relevant is it in 2025? Let's break it down.


1. Architecture and Key Features

Turing Architecture: The Foundation of Revolution

The RTX 2080 SUPER is built on the Turing architecture (12 nm, TSMC). It is the first generation of GPUs with hardware support for ray tracing (RTX) and tensor cores for AI calculations. Key technologies include:

- DLSS 1.0/2.0 — AI upscaling to boost FPS without loss of detail.

- Ray Tracing (RTX) — realistic lighting, shadows, and reflections.

- NVENC — a chip for video encoding, useful for streamers.

Note: FidelityFX is an AMD technology, but many games in 2025 support it on NVIDIA GPUs, improving image clarity.


2. Memory: Speed and Capacity

GDDR6 and Bandwidth

- Capacity: 8 GB.

- Memory Type: GDDR6 (not GDDR6X like in the RTX 3080+).

- Bus Width: 256-bit.

- Bandwidth: 496 GB/s.

Practical Impact

For gaming at 1440p and 4K with high settings, 8 GB is sufficient for most titles. However, in the latest AAA games (e.g., Cyberpunk 2077: Phantom Liberty Ultra), frame drops may occur due to insufficient memory. For professional tasks (3D scene rendering), the capacity is limited—it's better to consider cards with 12+ GB.


3. Gaming Performance

Average FPS in Popular Titles (2025)

- 1080p (Ultra):

- Apex Legends: 144 FPS.

- The Witcher 4: 75 FPS (with RTX and DLSS).

- 1440p (Ultra):

- Elden Ring 2: 60 FPS.

- Call of Duty: Future Warfare: 90 FPS (DLSS Quality).

- 4K (High/Ultra):

- Horizon Forbidden West PC: 45 FPS (DLSS Balanced).

RTX and DLSS

Activating ray tracing reduces FPS by 30–40%, but DLSS 2.0 compensates for losses. For instance, in Cyberpunk 2077 (4K, RTX Ultra) with DLSS, the card delivers a stable 40–50 FPS.


4. Professional Tasks

CUDA and OpenCL

- CUDA Cores: 3072. CUDA 7.5 support accelerates rendering in Blender, AutoCAD.

- Video Editing: In Adobe Premiere Pro, rendering a 4K video takes 20% less time compared to GTX 1080 Ti.

- Scientific Calculations: Suitable for beginner-level machine learning (TensorFlow), but lags behind the RTX 3060 with 12 GB of memory.

Advice: For complex tasks, it’s better to pay extra for an RTX 3060/4060 with more VRAM.


5. Power Consumption and Cooling

TDP and System Requirements

- TDP: 250 W.

- Recommended PSU: 650 W (80+ Gold).

Heat Management

- Standard coolers (Founders Edition) maintain temperatures up to 75°C under load.

- For overclocking, a liquid cooling system or a case with 3+ fans will be required.

Case Advice: At least 2 expansion slots, with ventilation from the bottom and top.


6. Comparison with Competitors

AMD Radeon RX 7700 XT (2024)

- Pros: 12 GB GDDR6, FSR 3.0, priced at $350.

- Cons: RTX 2080 SUPER excels in ray tracing due to DLSS.

NVIDIA RTX 3060 (2021)

- Pros: 12 GB, DLSS 3.0.

- Cons: 10–15% weaker in 4K.

Conclusion: The RTX 2080 SUPER is a good mid-range option for 1440p gaming with RTX.


7. Practical Tips

- Power Supply: 650 W, 8+8-pin connectors.

- Compatibility: PCIe 3.0 (works fine on PCIe 4.0/5.0 without losses).

- Drivers: NVIDIA regularly releases updates, but optimization for new games is slower than for the RTX 40 series.


8. Pros and Cons

Pros:

- Excellent performance in 1440p/4K with DLSS.

- Support for RTX and AI technologies.

- Affordable price ($300–400) for a High-End level.

Cons:

- 8 GB of VRAM is a weakness in 2025.

- High power consumption.

- Does not support DLSS 3.0 (only up to 2.0).


9. Final Conclusion: Who Should Get the RTX 2080 SUPER?

- Gamers: Those looking to play at 1440p/4K on high settings without overpaying for new releases.

- Streamers: Thanks to NVENC, video encoding puts minimal load on the CPU.

- Professionals: For basic video editing and 3D modeling.

Alternative: If the budget allows, the RTX 4060 (8 GB, $330) offers similar performance with DLSS 3.0 and lower TDP. However, the RTX 2080 SUPER remains a compelling choice for those who value proven reliability and are not chasing the latest technologies.


Updated in April 2025. Prices are current for new devices.

Basic

Label Name
NVIDIA
Platform
Desktop
Launch Date
July 2019
Model Name
GeForce RTX 2080 SUPER
Generation
GeForce 20
Base Clock
1650MHz
Boost Clock
1815MHz
Bus Interface
PCIe 3.0 x16
Transistors
13,600 million
RT Cores
48
Tensor Cores
?
Tensor Cores are specialized processing units designed specifically for deep learning, providing higher training and inference performance compared to FP32 training. They enable rapid computations in areas such as computer vision, natural language processing, speech recognition, text-to-speech conversion, and personalized recommendations. The two most notable applications of Tensor Cores are DLSS (Deep Learning Super Sampling) and AI Denoiser for noise reduction.
384
TMUs
?
Texture Mapping Units (TMUs) serve as components of the GPU, which are capable of rotating, scaling, and distorting binary images, and then placing them as textures onto any plane of a given 3D model. This process is called texture mapping.
192
Foundry
TSMC
Process Size
12 nm
Architecture
Turing

Memory Specifications

Memory Size
8GB
Memory Type
GDDR6
Memory Bus
?
The memory bus width refers to the number of bits of data that the video memory can transfer within a single clock cycle. The larger the bus width, the greater the amount of data that can be transmitted instantaneously, making it one of the crucial parameters of video memory. The memory bandwidth is calculated as: Memory Bandwidth = Memory Frequency x Memory Bus Width / 8. Therefore, when the memory frequencies are similar, the memory bus width will determine the size of the memory bandwidth.
256bit
Memory Clock
1937MHz
Bandwidth
?
Memory bandwidth refers to the data transfer rate between the graphics chip and the video memory. It is measured in bytes per second, and the formula to calculate it is: memory bandwidth = working frequency × memory bus width / 8 bits.
495.9 GB/s

Theoretical Performance

Pixel Rate
?
Pixel fill rate refers to the number of pixels a graphics processing unit (GPU) can render per second, measured in MPixels/s (million pixels per second) or GPixels/s (billion pixels per second). It is the most commonly used metric to evaluate the pixel processing performance of a graphics card.
116.2 GPixel/s
Texture Rate
?
Texture fill rate refers to the number of texture map elements (texels) that a GPU can map to pixels in a single second.
348.5 GTexel/s
FP16 (half)
?
An important metric for measuring GPU performance is floating-point computing capability. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy.
22.30 TFLOPS
FP64 (double)
?
An important metric for measuring GPU performance is floating-point computing capability. Double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy, while single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
348.5 GFLOPS
FP32 (float)
?
An important metric for measuring GPU performance is floating-point computing capability. Single-precision floating-point numbers (32-bit) are used for common multimedia and graphics processing tasks, while double-precision floating-point numbers (64-bit) are required for scientific computing that demands a wide numeric range and high accuracy. Half-precision floating-point numbers (16-bit) are used for applications like machine learning, where lower precision is acceptable.
11.373 TFLOPS

Miscellaneous

SM Count
?
Multiple Streaming Processors (SPs), along with other resources, form a Streaming Multiprocessor (SM), which is also referred to as a GPU's major core. These additional resources include components such as warp schedulers, registers, and shared memory. The SM can be considered the heart of the GPU, similar to a CPU core, with registers and shared memory being scarce resources within the SM.
48
Shading Units
?
The most fundamental processing unit is the Streaming Processor (SP), where specific instructions and tasks are executed. GPUs perform parallel computing, which means multiple SPs work simultaneously to process tasks.
3072
L1 Cache
64 KB (per SM)
L2 Cache
4MB
TDP
250W
Vulkan Version
?
Vulkan is a cross-platform graphics and compute API by Khronos Group, offering high performance and low CPU overhead. It lets developers control the GPU directly, reduces rendering overhead, and supports multi-threading and multi-core processors.
1.3
OpenCL Version
3.0
OpenGL
4.6
DirectX
12 Ultimate (12_2)
CUDA
7.5
Power Connectors
1x 6-pin + 1x 8-pin
Shader Model
6.6
ROPs
?
The Raster Operations Pipeline (ROPs) is primarily responsible for handling lighting and reflection calculations in games, as well as managing effects like anti-aliasing (AA), high resolution, smoke, and fire. The more demanding the anti-aliasing and lighting effects in a game, the higher the performance requirements for the ROPs; otherwise, it may result in a sharp drop in frame rate.
64
Suggested PSU
600W

Benchmarks

Shadow of the Tomb Raider 2160p
Score
47 fps
Shadow of the Tomb Raider 1440p
Score
93 fps
Shadow of the Tomb Raider 1080p
Score
132 fps
Cyberpunk 2077 2160p
Score
44 fps
Cyberpunk 2077 1440p
Score
51 fps
Cyberpunk 2077 1080p
Score
73 fps
Battlefield 5 2160p
Score
68 fps
Battlefield 5 1440p
Score
118 fps
Battlefield 5 1080p
Score
161 fps
GTA 5 2160p
Score
84 fps
GTA 5 1440p
Score
116 fps
FP32 (float)
Score
11.373 TFLOPS
3DMark Time Spy
Score
11831
Blender
Score
2155.51
Vulkan
Score
106450
OpenCL
Score
119659
Hashcat
Score
649725 H/s

Compared to Other GPU

Shadow of the Tomb Raider 2160p / fps
193 +310.6%
69 +46.8%
34 -27.7%
24 -48.9%
Shadow of the Tomb Raider 1440p / fps
292 +214%
128 +37.6%
67 -28%
49 -47.3%
Shadow of the Tomb Raider 1080p / fps
310 +134.8%
101 -23.5%
72 -45.5%
Cyberpunk 2077 2160p / fps
90 +104.5%
60 +36.4%
24 -45.5%
Cyberpunk 2077 1440p / fps
97 +90.2%
71 +39.2%
30 -41.2%
Cyberpunk 2077 1080p / fps
55 -24.7%
21 -71.2%
Battlefield 5 2160p / fps
194 +185.3%
106 +55.9%
56 -17.6%
Battlefield 5 1440p / fps
197 +66.9%
165 +39.8%
Battlefield 5 1080p / fps
204 +26.7%
192 +19.3%
GTA 5 2160p / fps
174 +107.1%
100 +19%
GTA 5 1440p / fps
191 +64.7%
73 -37.1%
FP32 (float) / TFLOPS
12.407 +9.1%
10.965 -3.6%
10.653 -6.3%
3DMark Time Spy
36233 +206.3%
16792 +41.9%
9097 -23.1%
Blender
15026.3 +597.1%
3514.46 +63%
1064 -50.6%
Vulkan
382809 +259.6%
140875 +32.3%
61331 -42.4%
34688 -67.4%
OpenCL
385013 +221.8%
167342 +39.8%
74179 -38%
56310 -52.9%
Hashcat / H/s
881523 +35.7%
705069 +8.5%
617807 -4.9%
530553 -18.3%