Radeon RX 6950 XT
58B
Memory16 GB
Memory TypeGDDR6
Boost Clock2310 MHz
TGP335 W
ArchitectureRDNA 2.0
Launch Price$1099
Benchmarks
Gaming59
Render59
TFLOPS (FP32)23.7
Geekbench OpenCL189,857
3DMarkTime Spy21,610
Steel Nomad Lite Score20,794
GB6 Compute Score189,857
Cinebench 2024 GPU12,357
G3D Mark Score28,058
Blender GPU2749.82
GB6 ML Single Precision33,294
GB6 ML Half Precision36,737
GB6 ML Quantized24,655
FLOPS (FP32)23.7 TFLOPS
Memory Bandwidth576 GB/s
Full specifications
3D Mark
Time Spy
21610
Solar Bay
89327
Port Royal
11269
Fire Strike
59854
Wild Life Extreme
40959
Night Raid
163309
GeekBench 6 OpenCL
Background Blur
382.1 img/sec
Face Detection
259 img/sec
Horizon Detection
6.93 Gpixels/sec
Edge Detection
10.2 Gpixels/sec
Gaussian Blur
8.39 Gpixels/sec
Feature Matching
1.48 Gpixels/sec
Stereo Matching
824.3 Gpixels/sec
Particle Physics
26538.1 FPS
API
OpenCL
Passmark Graphics
G2D Mark
1083
DirectX 11
298 FPS
DirectX 12
115 FPS
GPU Compute
14128 Ops/s
GeekBench 6 ML
Image Classification (SP)
14145
Image Segmentation (HP)
18828
Image Super Resolution (Q)
32309
Face Detection (HP)
49133
Pose Estimation (Q)
166767
Text Classification (SP)
4491
Machine Translation (HP)
6690
Object Detection (SP)
15446
Depth Estimation (Q)
56831
Style Transfer (SP)
367328
Framework
ONNX
Backend
DirectML
General
Vendor
Amd
Build
Discrete
Released
May 10, 2022
Launch price (MSRP)
$1099
Case
Desktop
Purpose
Gaming
Segment
High-end
Architecture
RDNA 2.0
GPU Codename
Navi 21
Nvidia Equivalent
- GeForce RTX 4070 SUPER
Recommended CPU
- Intel Core i7 12700K or above
Graphics Processing Unit
Base Clock
1860 MHz
Boost Clock
2310 MHz
Shading Units
5120
Texture Mapping Units (TMUs)
320
Render Output Units (ROPs)
128
Ray-tracing Cores
80
L1 Cache
128KB per cluster
L2 Cache
4MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
296 GPixel/s
Texture Fill Rate
739 GTexel/s
Physical
Interface
PCIe 4.0 x16
TGP
335 W
Manufacturing
TSMC
Fabrication Process
7 nm
Die Size
520 mm²
Transistor Count
26 billion
Transistor Density
50 MTr/mm²
Memory
Memory Type
GDDR6
Memory Size
16 GB
Memory Clock
2250 MHz
Effective Memory Speed
18000 Mbps
Bus
256-bit
ECC
No
API
DirectX
12
Vulkan
1.3
OpenGL
4.6
OpenCL
2.1
Ray Tracing
Yes
DLSS
No
DisplayPort
1.4a
Specifications compiled from NanoReview. Last updated 2026-09-29.
More graphics cards
View all →97
Nvidia
Nvidia RTX Pro 6000 Blackwell
- Memory96 GB
- Memory TypeGDDR7
- Boost Clock2617 MHz
- TGP600 W
Desktop GPU
96
Nvidia
GeForce RTX 5090
- Memory32 GB
- Memory TypeGDDR7
- Boost Clock2407 MHz
- TGP575 W
Desktop GPU
89
Nvidia
GeForce RTX 4090
- Memory24 GB
- Memory TypeGDDR6X
- Boost Clock2520 MHz
- TGP450 W
Desktop GPU
84
Nvidia
GeForce RTX 5080
- Memory16 GB
- Memory TypeGDDR7
- Boost Clock2617 MHz
- TGP360 W
Desktop GPU