Head to head
Compare Graphics Cards
Pick up to 4. Winners are highlighted in green ▲.
1 selected
Key specs
Memory
6 GB
Memory Type
GDDR5
Boost Clock
1076 MHz
TGP
250 W
Architecture
Maxwell 2.0
Launch Price
$649
Benchmarks
Rating
21
Gaming
19
Render
27
TFLOPS (FP32)
6.1
Geekbench OpenCL
49,950
3DMarkTime Spy
5855
Steel Nomad Lite Score
5913
GB6 Compute Score
49,950
Cinebench 2024 GPU
3352
G3D Mark Score
13,619
Blender GPU
532.9
GB6 ML Single Precision
7711
GB6 ML Half Precision
7464
GB6 ML Quantized
5338
FLOPS (FP32)
6.1 TFLOPS
Memory Bandwidth
336.6 GB/s
3D Mark
Time Spy
5855
Port Royal
3250
Fire Strike
19,504
Wild Life Extreme
11,870
Night Raid
70,127
GeekBench 6 OpenCL
Background Blur
134.8 img/sec
Face Detection
59.8 img/sec
Horizon Detection
2.37 Gpixels/sec
Edge Detection
3.79 Gpixels/sec
Gaussian Blur
3.46 Gpixels/sec
Feature Matching
0.22 Gpixels/sec
Stereo Matching
191.9 Gpixels/sec
Particle Physics
4183.6 FPS
API
OpenCL
Passmark Graphics
G2D Mark
849
DirectX 11
106 FPS
DirectX 12
55 FPS
GPU Compute
6093 Ops/s
GeekBench 6 ML
Image Classification (SP)
3173
Image Segmentation (HP)
4916
Image Super Resolution (Q)
7407
Face Detection (HP)
8201
Pose Estimation (Q)
27,221
Text Classification (SP)
1675
Machine Translation (HP)
2607
Object Detection (SP)
4123
Depth Estimation (Q)
11,660
Style Transfer (SP)
55,570
Framework
ONNX
Backend
DirectML
General
Vendor
Nvidia
Build
Discrete
Released
June 2, 2015
Launch price (MSRP)
$649
Case
Desktop
Purpose
Gaming
Segment
High-end
Architecture
Maxwell 2.0
GPU Codename
GM200
Successor
- GeForce RTX 3080 Ti
Graphics Processing Unit
Base Clock
1000 MHz
Boost Clock
1076 MHz
Shading Units
2816
Texture Mapping Units (TMUs)
176
Render Output Units (ROPs)
96
Compute Units (Pipelines)
22
Tensor Cores
No
Ray-tracing Cores
No
L1 Cache
48KB per cluster
L2 Cache
3MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
103 GPixel/s
Texture Fill Rate
189 GTexel/s
Physical
Interface
PCIe 3.0 x16
TGP
250 W
Manufacturing
TSMC
Fabrication Process
28 nm
Die Size
601 mm²
Transistor Count
8 billion
Transistor Density
13.31 MTr/mm²
Memory
Memory Type
GDDR5
Memory Size
6 GB
Memory Clock
1753 MHz
Effective Memory Speed
7000 Mbps
Bus
384-bit
ECC
No
API
DirectX
12
Vulkan
1.3
OpenGL
4.6
OpenCL
3.0
CUDA
5.2
Ray Tracing
No
DLSS
No
DisplayPort
1.2