AMD Radeon RX 6800 XT

AMD Radeon RX 6800 XT

AMD Radeon RX 6800 XT: A Guide to the Flagship Graphics Card of 2025

Overview of capabilities, performance, and practical recommendations


1. RDNA 2 Architecture: The Power Foundation

The AMD Radeon RX 6800 XT is built on the RDNA 2 architecture, which marked a breakthrough for AMD in the high-performance GPU segment. This architecture utilizes a 7nm manufacturing process from TSMC, providing high transistor density and energy efficiency.

Key Features:

- Ray Accelerators: Hardware units to accelerate ray tracing. Compared to NVIDIA's RTX 3000 series, AMD's RT performance is weaker, but by 2025, drivers and game optimizations have significantly improved this aspect.

- Infinity Cache: 128MB of cache memory reduces latency and enhances efficiency when working with GDDR6.

- FidelityFX Super Resolution (FSR): An upscaling technology that in version FSR 3.1 (current in 2025) has nearly caught up to NVIDIA's DLSS in image quality, supporting over 150 games.


2. Memory: 16GB GDDR6 for the Future

The RX 6800 XT is equipped with 16GB of GDDR6 memory with a 256-bit bus. The bandwidth reaches 512 GB/s, and thanks to the Infinity Cache, practical bandwidth in real-world scenarios is even higher — up to ~1.5 TB/s.

Impact on Performance:

- The memory capacity is sufficient for gaming at 4K with ultra textures and professional tasks like 3D scene rendering.

- In VRAM-hungry games, such as Cyberpunk 2077: Phantom Liberty (2024), the card does not experience buffer overrun even at maximum settings.


3. Gaming Performance: 4K Without Compromises

In 2025, the RX 6800 XT remains relevant for most AAA titles. Examples of FPS (without enabling FSR):

- Cyberpunk 2077: 55–60 FPS at 4K (Ultra, ray tracing off), 35–40 FPS with ray tracing.

- Starfield: 60–65 FPS at 1440p (Ultra), 45–50 FPS at 4K.

- Call of Duty: Black Ops 6: 120+ FPS at 1440p (Extreme).

Ray Tracing:

With RT enabled, performance drops by 30–40%, but with FSR 3.1 Quality, you can regain up to 70% of lost frames. In this regard, the card falls short compared to NVIDIA's RTX 4080 but wins in terms of price.


4. Professional Tasks: Not Just Gaming

Although the RX 6800 XT is designed for gamers, it also handles work workloads well:

- 3D Rendering: In Blender (via HIP), the rendering speed is comparable to NVIDIA's RTX 3070 Ti.

- Video Editing: In DaVinci Resolve, the card shows smooth performance with 8K materials thanks to its memory capacity.

- Scientific Calculations: Support for OpenCL and ROCm allows the use of the GPU for machine learning, but the ecosystem is still less developed compared to CUDA.


5. Power Consumption and Cooling: Demanding but Manageable

- TDP: 300W. Peak power consumption can reach up to 350W.

- Cooling Recommendations:

- A case with at least 3 fans: for example, Lian Li Lancool III or Fractal Design Meshify 2.

- Optimal coolers: Triple-slot solutions (Sapphire Nitro+) or hybrid liquid cooling (ASUS ROG Strix LC).

- Temperatures: At stock settings, the GPU heats up to 75–80°C, but throttling can be avoided.


6. Comparison with Competitors: The Battle for Value

- NVIDIA RTX 4080: 15–20% faster in ray tracing and supports DLSS 4.0, but costs $900–1000 compared to $550–600 for the RX 6800 XT.

- AMD Radeon RX 7800 XT: The junior model of 2024. Lags behind in 4K by 10–15%, but is more energy-efficient.

- Intel Arc A770: A more budget-friendly alternative ($350), but falls short in professional tasks and 4K gaming.

Conclusion: The RX 6800 XT offers the best value in the $500–600 segment, especially for those who do not need top-tier RT.


7. Practical Tips: Building Your System Right

- Power Supply: At least 750W (recommended 850W for margin). The best options are Corsair RM850x or Seasonic Focus GX-850.

- Compatibility:

- PCIe 4.0 x16 is essential for full performance.

- Supports AMD AM5 and Intel LGA 1700 motherboards.

- Drivers: Adrenalin 2025 Edition is stable, but if there are issues with new games, it is advisable to revert to WHQL versions.


8. Pros and Cons

Pros:

- Exceptional performance in 4K.

- 16GB of memory — future-proofing.

- FSR 3.1 nearly matches DLSS.

- Optimal price-to-performance ratio.

Cons:

- Ray tracing performance is weaker than NVIDIA’s.

- High power consumption.

- Lack of hardware support for AI cores (like Tensor Cores).


9. Final Thoughts: Who is the RX 6800 XT For?

This graphics card is an ideal choice for:

- Gamers who want to play in 4K without upscaling or use FSR to boost FPS.

- Enthusiasts on a budget: for $550–600, you get 90% of the performance of the RTX 4080 in traditional rendering.

- Professionals working with 3D and video: the memory capacity and OpenCL support make it a versatile tool.

In 2025, the RX 6800 XT remains relevant thanks to software updates and price drops. If you do not require top-tier RT and AI features from NVIDIA, this is the best offer on the market.


Prices are accurate as of April 2025. Check for sales and updated performance tests in current games before purchasing.

Basic

Label Name
AMD
Platform
Desktop
Launch Date
October 2020
Model Name
Radeon RX 6800 XT
Generation
Navi II
Base Clock
1825MHz
Boost Clock
2250MHz
Bus Interface
PCIe 4.0 x16
Transistors
26,800 million
RT Cores
72
Compute Units
72
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.
288
Foundry
TSMC
Process Size
7 nm
Architecture
RDNA 2.0

Memory Specifications

Memory Size
16GB
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
2000MHz
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.
512.0 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.
288.0 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.
648.0 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.
41.47 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.
1296 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.
20.325 TFLOPS

Miscellaneous

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.
4608
L1 Cache
128 KB per Array
L2 Cache
4MB
TDP
300W
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
2.1
OpenGL
4.6
DirectX
12 Ultimate (12_2)
Power Connectors
2x 8-pin
Shader Model
6.5
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.
128
Suggested PSU
700W

Benchmarks

Shadow of the Tomb Raider 2160p
Score
71 fps
Shadow of the Tomb Raider 1440p
Score
131 fps
Shadow of the Tomb Raider 1080p
Score
192 fps
Cyberpunk 2077 2160p
Score
61 fps
Cyberpunk 2077 1440p
Score
68 fps
Cyberpunk 2077 1080p
Score
100 fps
Battlefield 5 2160p
Score
106 fps
Battlefield 5 1440p
Score
183 fps
Battlefield 5 1080p
Score
203 fps
GTA 5 2160p
Score
109 fps
GTA 5 1440p
Score
135 fps
GTA 5 1080p
Score
182 fps
FP32 (float)
Score
20.325 TFLOPS
3DMark Time Spy
Score
19904
Blender
Score
2384
Vulkan
Score
156538
OpenCL
Score
150221
Hashcat
Score
971947 H/s

Compared to Other GPU

Shadow of the Tomb Raider 2160p / fps
193 +171.8%
45 -36.6%
34 -52.1%
24 -66.2%
Shadow of the Tomb Raider 1440p / fps
292 +122.9%
67 -48.9%
49 -62.6%
Shadow of the Tomb Raider 1080p / fps
310 +61.5%
101 -47.4%
72 -62.5%
Cyberpunk 2077 2160p / fps
90 +47.5%
24 -60.7%
Cyberpunk 2077 1440p / fps
185 +172.1%
35 -48.5%
Cyberpunk 2077 1080p / fps
203 +103%
48 -52%
Battlefield 5 2160p / fps
194 +83%
56 -47.2%
Battlefield 5 1440p / fps
203 +10.9%
Battlefield 5 1080p / fps
213 +4.9%
169 -16.7%
139 -31.5%
122 -39.9%
GTA 5 2160p / fps
174 +59.6%
GTA 5 1440p / fps
191 +41.5%
73 -45.9%
GTA 5 1080p / fps
231 +26.9%
156 -14.3%
141 -22.5%
86 -52.7%
FP32 (float) / TFLOPS
21.58 +6.2%
19.1 -6%
3DMark Time Spy
36233 +82%
9097 -54.3%
Blender
15026.3 +530.3%
3514.46 +47.4%
1064 -55.4%
Vulkan
382809 +144.5%
91662 -41.4%
61331 -60.8%
34688 -77.8%
OpenCL
385013 +156.3%
167342 +11.4%
74179 -50.6%
56310 -62.5%
Hashcat / H/s
2602280 +167.7%
1198430 +23.3%
883336 -9.1%
881523 -9.3%