GPU Wiki

AMD Radeon RX 6800 XT vs GeForce RTX 3070

Swap Clear comparison
Edit GPUs
Add a third or fourth GPU

Key Differences

  • No game was measured on every one of these cards on one shared test system, so there is no speed comparison to make.
  • RX 6800 XT has the most memory: 16 GB against 8 GB.
  • RX 6800 XT has the most memory bandwidth: 512.0 GB/s against 448 GB/s.
  • RTX 3070 draws the least power: 220 W against 300 W.
  • Core counts are not comparable across these architectures.
Spec AMD Radeon RX 6800 XT AMD GeForce RTX 3070
Overview
Product name AMD Radeon RX 6800 XT NVIDIA GeForce RTX 3070
Architecture RDNA 2 Ampere
Generation / family Radeon RX 6000 Series GeForce RTX 30 Series
GPU codename Navi 21 XT GA104
Launch date 2020-11-18 2020-10-29
Launch MSRP 649 Unknown
Market segment Desktop, Enthusiast Desktop in GeForce RTX 30 Series
Board type / entry type Reference GPU Reference GPU
GPU
Process node 7 nm Samsung 8 nm
Die size 520 mm² 392 mm²
Transistor count 26800 million 17.4 billion
GPU chip Navi 21 GA104
SM / multiprocessor count 72 46
Shader processors Raw counts do not scale linearly across architectures or generations. 4608 Stream Processors 5888 CUDA Cores
AI units Dedicated AI silicon differs significantly across vendors. Not directly comparable. Unknown AI Accelerators 184 Tensor Cores
RT units Dedicated RT unit counts do not scale the same way across vendors. 72 Ray Accelerators 46 RT Cores
ROPs 128 96
TMUs 256 184
Clocks
Base / Core clock 1825 MHz 1,500 MHz
Boost clock 2250 MHz 1,725 MHz
Memory clock 2000 MHz 1,750 MHz
Memory
Memory size 16 GB 8 GB
Memory type GDDR6 GDDR6
Memory bus width 256-bit 256-bit
Memory bandwidth 512.0 GB/s 448 GB/s
Bus / Interface
Bus interface PCIe 4.0 x16 PCIe 4.0 x16
AGP / PCI / PCIe distinction PCIe PCIe
Power
TDP / TBP / board power 300 W 220 W
Recommended PSU 750 W 650 W
Power connectors 2x 8-pin 1x 12-pin
Slot width Dual-slot Dual-slot, 242 mm length
Display / Media
Display outputs 1x HDMI 2.1, 2x DisplayPort 1.4a, 1x USB Type-C 1x HDMI 2.1, 3x DisplayPort 1.4a
Features
DirectX support DirectX 12 Ultimate DirectX 12.2
OpenGL support OpenGL 4.6 OpenGL 4.6
Vulkan support Vulkan 1.3 Vulkan 1.4
CUDA support Not applicable 8.6
Shader Model 6.8 6.8
Ray tracing support Hardware RT units present Hardware RT units present
Performance / Benchmarks
FP32 throughput 18.43 TFLOPS 20.31 TFLOPS
FP16 throughput 41.47 TFLOPS 20.31 TFLOPS
Muted cells indicate unavailable, not applicable, or not directly comparable specifications.

Frame rates compare runs of the same game at the same quality preset on one test system. DLAA counts as native resolution, because it applies anti-aliasing at full render resolution rather than upscaling; DLSS and FSR upscaling are never counted as native. Where a capture named ray tracing without a readable on or off value, it is read as on.