RX 6800
RX 6800 Review & Specifications
The RX 6800 is based on the RDNA 2.0 architecture and manufactured using the 7 nm process node. It was launched approximately 5 years, 8 months ago, originally priced at $579. It features 3840 cores, including 60 compute units (SMs), 240 texture mapping units (TMUs), and 96 render output units (ROPs). For ray tracing and AI-accelerated tasks, it also includes 60 dedicated RT cores and None Tensor cores, enabling advanced rendering and upscaling features where supported. It has a base clock of 1700 MHz and a boost clock reaching up to 2105 MHz. The RX 6800 comes equipped with 16 GB of GDDR6 memory across a 256-bit bus. Memory runs at 2000 MHz and delivers a total memory bandwidth of 512 GB/s.
This GPU has a moderate thermal design power (TDP) of 250 W. A PC case with good airflow and a quality power supply are required for stable operation. Due to the moderate TDP, this GPU is suitable for small form factor builds with somewhat limited airflow.
RX 6800 Performance
RX 6800 is a mid-range graphics card, scoring 44.00% in relative gaming performance. Thanks to 16 GB of VRAM, it offers excellent 1440p performance and can handle 4K gaming with optimized settings or the help of DLSS, FSR, and frame generation. Great for users targeting 100+ FPS at 1440p or playable 4K in lighter titles.
The RX 6800 includes a substantial 16 GB of VRAM, making it capable of high to ultra settings in most games at up to 4K resolution. It performs well in demanding creative workloads like 4K video editing, RAW image manipulation, and 3D rendering. For AI and machine learning, AMD GPUs are gradually improving: while they still lack CUDA support, some frameworks now offer experimental or partial support via ROCm — allowing limited use with models like Stable Diffusion. However, software compatibility remains inconsistent, and performance is typically lower than NVIDIA equivalents. Overall, this GPU is a strong choice for gamers and creators, but only suitable for light or hobbyist AI workloads.
In terms of gaming value, RX 6800 offers excellent performance per dollar, achieving 82.4% efficiency relative to the best in this category. It is an outstanding choice for users seeking a cost-effective yet powerful solution, with ample VRAM ensuring strong future-proofing.
General Information
| GPU Name | RX 6800 |
|---|---|
| GPU Code Name | Navi 21 |
| Release Price | $579 |
| Selected Model | Speedster SWFT319 AMD Radeon RX 6800 Gaming Graphics Card with 16GB GDDR6, AMD RDNA 2 RX-68XLAQBD9 |
| Current Price Amazon | $450 |
| Amazon Price Updated | 1 week, 4 days ago |
| Launch Date | 5 years, 8 months ago |
| GPU Available | True |
| Architecture | RDNA 2.0 |
|---|---|
| Foundry | TSMC |
| Process | 7 |
| Transistors | 26800 million |
| Die Size | 520 mm² |
| Bus Interface | PCIe 4.0 x16 |
| TDP | 250 W |
| Cores | 3840 |
|---|---|
| CUs (SMs) | 60 |
| TMUs | 240 |
| ROPs | 96 |
| RT Cores | 60 |
| Tensor Cores | None |
| L0 Cache | 32 KB per WGP |
| L1 Cache | 128 KB per Array |
| L2 Cache | 4 MB |
| L3 Cache | 128 MB |
| Base Clock | 1700 MHz |
|---|---|
| Boost Clock | 2105 MHz |
| Memory Size - Type | 16 GB GDDR6 |
|---|---|
| Memory Bus Width | 256 bit |
| Memory Clock | 2000 MHz |
| Memory Bandwidth | 512 GB/s |
| DirectX | 12 Ultimate (12_2) |
|---|---|
| OpenGL | 4.6 |
| OpenCL | 2.1 |
| Vulkan | 1.4 |
| Shader Model | 6.8 |
Theoretical Performance
| Pixel Rate | 202.10 GPixel/s |
|---|---|
| Texture Rate | 505.20 GTexel/s |
| FP16 | 32.33 TFLOPS |
| FP32 | 16.17 TFLOPS |
| FP64 | 1010.00 GFLOPS |
Gaming Performance Chart
RX 6800 Compared to Similar Performance GPUs
GPU Price / Performance Table
| GPU (Desc) | Price (Desc) | Gaming_1080p (Desc) | Gaming_1440p (Desc) | Gaming_2160p (Desc) | Game_1440p/Price (Desc) |
|---|---|---|---|---|---|
|
$630
|
↑
18.9%
|
51.4%
|
43.1%
|
35.8%
|
67.7%
|
|
|
$600
|
0.0%
|
49.2%
|
42.7%
|
35.6%
|
70.4%
|
|
|
$565
|
↑
0.0%
|
45.2%
|
38.5%
|
31.7%
|
67.5%
|
|
|
$410
|
0.0%
|
43.9%
|
38.2%
|
31.5%
|
92.2%
|
|
|
$450
|
0.0%
|
44.0%
|
37.4%
|
32.1%
|
82.4%
|
|
|
$430
|
0.0%
|
44.6%
|
36.6%
|
25.7%
|
84.2%
|
|
|
$500
|
0.0%
|
42.8%
|
36.0%
|
29.9%
|
71.2%
|
|
|
$400
|
0.0%
|
42.5%
|
35.7%
|
30.6%
|
88.4%
|
|
|
$340
|
0.0%
|
40.3%
|
33.8%
|
28.5%
|
98.4%
|
GPU Specification Table
| GPU (Desc) | Architecture | Shader/TMU/ROP/RT | Base/Boost Clock | Memory | Mem Clock/Bandwidth | TDP |
|---|---|---|---|---|---|---|
| RTX 4070 | AD104 / 5 nm nm / Ada Lovelace | 5888 / 184 / 64 / 46 | 1920 MHz / 2475 MHz | 12 GB GDDR6X / 192 bit | 1313 MHz / 504 GB/s | 200 W |
| RX 6800 XT | Navi 21 / 7 nm / RDNA 2.0 | 4608 / 288 / 128 / 72 | 1825 MHz / 2250 MHz | 16 GB GDDR6 / 256 bit | 2000 MHz / 512 GB/s | 300 W |
| RTX 5060 Ti 16GB | GB206 / 5 nm nm / Blackwell 2.0 | 4608 / 144 / 48 / 36 | 2407 MHz / 2572 MHz | 16 GB GDDR7 / 128 bit | 1750 MHz / 448 GB/s | 180 W |
| RX 7700 XT | Navi 32 / 5 nm / RDNA 3.0 | 3456 / 216 / 96 / 54 | 1435 MHz / 2544 MHz | 12 GB GDDR6 / 192 bit | 2250 MHz / 432 GB/s | 245 W |
| RX 6800 | Navi 21 / 7 nm / RDNA 2.0 | 3840 / 240 / 96 / 60 | 1700 MHz / 2105 MHz | 16 GB GDDR6 / 256 bit | 2000 MHz / 512 GB/s | 250 W |
| RTX 5060 Ti 8GB | GB206 / 5 nm nm / Blackwell 2.0 | 4608 / 144 / 48 / 36 | 2407 MHz / 2572 MHz | 8 GB GDDR7 / 128 bit | 1750 MHz / 448 GB/s | 180 W |
| RX 9060 XT 16GB | Navi 44 / 4 nm / RDNA 4.0 | 2048 / 128 / 64 / 32 | 1700 MHz / 3130 MHz | 16 GB GDDR6 / 128 bit | 2518 MHz / 322 GB/s | 160 W |
| RTX 3070 Ti | GA104 / 8 nm nm / Ampere | 6144 / 192 / 96 / 48 | 1575 MHz / 1770 MHz | 8 GB GDDR6X / 256 bit | 1188 MHz / 608 GB/s | 290 W |
| RTX 3070 | GA104 / 8 nm nm / Ampere | 5888 / 184 / 96 / 46 | 1500 MHz / 1725 MHz | 8 GB GDDR6 / 256 bit | 1750 MHz / 448 GB/s | 220 W |
Add Comment on RX 6800