NVIDIA GeForce RTX 2080 Ti

NVIDIA GeForce RTX 2080 Ti

NVIDIA GeForce RTX 2080 Ti in 2025: Is it Worth Getting the Legend of the Past?

Current review for gamers and professionals


Introduction

The NVIDIA GeForce RTX 2080 Ti is a graphics card that revolutionized the industry in 2018 by introducing real-time ray tracing to the world. Seven years later, in 2025, it remains a topic of debate: some view it as outdated, while others see it as a budget-friendly option for building a PC. In this article, we will analyze how relevant the RTX 2080 Ti is today and who it is suitable for.


Architecture and Key Features

Turing Architecture: The Foundation for the Future

The RTX 2080 Ti is built on the Turing architecture (12 nm), which marked NVIDIA's first step towards hybrid rendering. Key components include:

- 4352 CUDA cores — provide high parallel performance.

- RT cores — responsible for ray tracing.

- Tensor cores — the foundation for DLSS (Deep Learning Super Sampling).

Technologies That Changed the Industry

- RTX (Ray Tracing): The first mass support for realistic lighting and shadows. By 2025, ray tracing has become the standard, but hardware requirements have increased.

- DLSS 2.0: Artificial intelligence enhances image resolution with minimal quality loss. Modern games increasingly use DLSS 3.5+, which is not available on the RTX 20 series.

- Support for FidelityFX Super Resolution (FSR): AMD's technology works on any GPU, including the RTX 2080 Ti, compensating for the lack of DLSS 3+.

Manufacturing Process

The 12 nm process from TSMC looks archaic in the face of the 4 nm chips in the RTX 40 series. However, Turing remains energy-efficient for its generation.


Memory: Speed vs. Capacity

- Type and Size: 11 GB GDDR6. By 2025, this is insufficient for 4K gaming with maximum textures (for example, "Cyberpunk 2077: Phantom Liberty" requires 12+ GB).

- Bandwidth: 616 GB/s. This falls short compared to GDDR6X (RTX 3080 – 760 GB/s) and HBM2e (Radeon RX 7900 XTX – 960 GB/s).

- Impact on Performance: Adequate memory for gaming up to 1440p. In 4K, FPS drops are possible due to buffer filling.

Tip: Disable RTX or lower texture quality in 4K to avoid "stutters."


Gaming Performance: Numbers and Realities of 2025

Testing in Popular Titles (Average FPS):

- "Cyberpunk 2077" (4K, Ultra, RTX Medium, DLSS Balanced): 34-38 FPS. Without RTX – 55-60 FPS.

- "Starfield" (1440p, Ultra, FSR 2.1 Quality): 60-65 FPS.

- "Call of Duty: Black Ops 6" (1080p, Ultra): 144+ FPS.

Resolutions:

- 1080p: Ideal for esports titles (CS2, Valorant) – stable 200+ FPS.

- 1440p: The optimal choice for AAA games, balancing quality and FPS.

- 4K: Requires compromises. For example, in "Horizon Forbidden West" (High, without RTX) – 40-45 FPS.

Ray Tracing: Even in 2025, the RTX 2080 Ti handles ray tracing at Low/Medium settings, but in projects like "Alan Wake 3," FPS drops to 25-30 without DLSS.


Professional Tasks: Not Just Gaming

Video Editing:

- Premiere Pro: 4K video rendering in H.264 is 30% faster than the GTX 1080 Ti.

- DaVinci Resolve: CUDA acceleration is stable, but newer GPUs (e.g., RTX 4070) process 8K twice as fast.

3D Modeling:

- Blender (Cycles): The 2080 Ti shows 1420 samples/min in the BMW test. In comparison, the RTX 4060 – 2100 samples/min.

Scientific Calculations:

- CUDA and OpenCL support are useful for basic machine learning tasks. However, for training neural networks with billions of parameters, cards with 16+ GB of memory are preferable.


Power Consumption and Heat Output

- TDP: 260 W. In comparison, the RTX 4070 consumes 200 W while offering better performance.

- Recommendations:

- Power Supply: At least 650 W (preferably 750 W for headroom).

- Cooling: A case with 3+ fans is required. Ideally, a liquid cooling system or a tower cooler with 3+ heat pipes.

- Overclocking: Increases consumption to 300 W. Not recommended without a top-tier cooling system.

Tip: Avoid compact cases. The best options are the Fractal Design Meshify 2 or Lian Li Lancool III.


Comparison with Competitors

NVIDIA RTX 4060 ($399):

- Comparable performance at 1440p but lower at 4K.

- Supports DLSS 3.5 with lower power consumption.

AMD Radeon RX 7700 XT ($449):

- 12 GB GDDR6, better performance in Vulkan projects (e.g., "Red Dead Redemption 2").

- FSR 3.0 vs DLSS 2.0: parity.

Intel Arc A770 ($349):

- 16 GB memory, but driver optimizations still lag behind NVIDIA.

Conclusion: The RTX 2080 Ti is only advantageous on the secondary market (around $250). Newer cards offer better price-to-performance ratios.


Practical Tips

- Power Supply: 80+ Gold or better. Examples: Corsair RM750x, Be Quiet! Straight Power 11.

- Compatibility: PCIe 3.0 x16. Works without loss on motherboards with PCIe 4.0/5.0.

- Drivers: NVIDIA regularly releases updates, but new features (e.g., Reflex Low Latency 2.0) are not available.

Tip for Gamers: Use FSR 3.0 instead of DLSS 2.0 to increase FPS in modern games.


Pros and Cons

Pros:

- Affordable price on the secondary market.

- Support for basic Ray Tracing and DLSS.

- Reliability and a time-tested design.

Cons:

- High power consumption.

- Only 11 GB of memory.

- Lack of modern technologies (DLSS 3.5+, AV1 encoding).


Final Conclusion: Who Should Consider the RTX 2080 Ti in 2025?

This graphics card is a choice for:

1. Gamers on a Budget who are willing to make compromises at 4K.

2. Upgrade Enthusiasts building PCs with second-hand components.

3. Professionals who need CUDA support for light tasks.

However, if you want to enjoy new games at maximum settings with RTX, consider the RTX 4060 or RX 7700 XT. The RTX 2080 Ti remains a legend, but time does not stand still.

Basic

Label Name
NVIDIA
Platform
Desktop
Launch Date
September 2018
Model Name
GeForce RTX 2080 Ti
Generation
GeForce 20
Base Clock
1350MHz
Boost Clock
1545MHz
Bus Interface
PCIe 3.0 x16
Transistors
18,600 million
RT Cores
68
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.
544
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.
272
Foundry
TSMC
Process Size
12 nm
Architecture
Turing

Memory Specifications

Memory Size
11GB
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.
352bit
Memory Clock
1750MHz
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.
616.0 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.
136.0 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.
420.2 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.
26.90 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.
420.2 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.
13.181 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.
68
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.
4352
L1 Cache
64 KB (per SM)
L2 Cache
0MB
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
2x 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.
88
Suggested PSU
600W

Benchmarks

Shadow of the Tomb Raider 2160p
Score
57 fps
Shadow of the Tomb Raider 1440p
Score
107 fps
Shadow of the Tomb Raider 1080p
Score
148 fps
Cyberpunk 2077 2160p
Score
51 fps
Cyberpunk 2077 1440p
Score
61 fps
Cyberpunk 2077 1080p
Score
84 fps
Battlefield 5 2160p
Score
79 fps
Battlefield 5 1440p
Score
141 fps
Battlefield 5 1080p
Score
186 fps
GTA 5 2160p
Score
92 fps
GTA 5 1440p
Score
149 fps
GTA 5 1080p
Score
176 fps
FP32 (float)
Score
13.181 TFLOPS
3DMark Time Spy
Score
14965
Blender
Score
2640.18
Vulkan
Score
132317
OpenCL
Score
147055

Compared to Other GPU

Shadow of the Tomb Raider 2160p / fps
193 +238.6%
69 +21.1%
34 -40.4%
24 -57.9%
Shadow of the Tomb Raider 1440p / fps
292 +172.9%
128 +19.6%
67 -37.4%
49 -54.2%
Shadow of the Tomb Raider 1080p / fps
310 +109.5%
101 -31.8%
72 -51.4%
Cyberpunk 2077 2160p / fps
90 +76.5%
60 +17.6%
24 -52.9%
Cyberpunk 2077 1440p / fps
185 +203.3%
35 -42.6%
Cyberpunk 2077 1080p / fps
203 +141.7%
114 +35.7%
48 -42.9%
Battlefield 5 2160p / fps
194 +145.6%
106 +34.2%
56 -29.1%
Battlefield 5 1440p / fps
203 +44%
165 +17%
Battlefield 5 1080p / fps
213 +14.5%
139 -25.3%
122 -34.4%
GTA 5 2160p / fps
174 +89.1%
100 +8.7%
GTA 5 1440p / fps
191 +28.2%
GTA 5 1080p / fps
231 +31.3%
156 -11.4%
141 -19.9%
86 -51.1%
FP32 (float) / TFLOPS
14.168 +7.5%
13.612 +3.3%
12.913 -2%
12.603 -4.4%
3DMark Time Spy
36233 +142.1%
16792 +12.2%
9097 -39.2%
Blender
15026.3 +469.1%
3514.46 +33.1%
1064 -59.7%
552 -79.1%
Vulkan
382809 +189.3%
140875 +6.5%
61331 -53.6%
34688 -73.8%
OpenCL
385013 +161.8%
167342 +13.8%
75816 -48.4%
57474 -60.9%