GeForce GTX 1070 Ti
23D
Memory8 GB
Memory TypeGDDR5
Boost Clock1683 MHz
TGP180 W
ArchitecturePascal
Benchmarks
Gaming22
Render28
TFLOPS (FP32)8.2
Geekbench OpenCL57,735
3DMarkTime Spy6842
Steel Nomad Lite Score6671
GB6 Compute Score57,735
Cinebench 2024 GPU3806
G3D Mark Score14,668
Blender GPU626.69
GB6 ML Single Precision8949
GB6 ML Half Precision8769
GB6 ML Quantized6546
FLOPS (FP32)8.2 TFLOPS
Memory Bandwidth256.3 GB/s
Full specifications
3D Mark
Time Spy
6842
Solar Bay
18306
Port Royal
1554
Fire Strike
20113
Wild Life Extreme
13255
Night Raid
78888
GeekBench 6 OpenCL
Background Blur
149.2 img/sec
Face Detection
67.6 img/sec
Horizon Detection
2.36 Gpixels/sec
Edge Detection
3.57 Gpixels/sec
Gaussian Blur
4.32 Gpixels/sec
Feature Matching
0.27 Gpixels/sec
Stereo Matching
209.6 Gpixels/sec
Particle Physics
6584.9 FPS
API
OpenCL
Passmark Graphics
G2D Mark
876
DirectX 11
106 FPS
DirectX 12
52 FPS
GPU Compute
7166 Ops/s
GeekBench 6 ML
Image Classification (SP)
3473
Image Segmentation (HP)
5149
Image Super Resolution (Q)
9722
Face Detection (HP)
9306
Pose Estimation (Q)
34870
Text Classification (SP)
2139
Machine Translation (HP)
2424
Object Detection (SP)
4566
Depth Estimation (Q)
14316
Style Transfer (SP)
88984
Framework
ONNX
Backend
DirectML
General
Vendor
Nvidia
Build
Discrete
Released
November 2, 2017
Case
Desktop
Purpose
Gaming
Segment
Mid-range
Architecture
Pascal
GPU Codename
GP104
AMD Equivalent
- Radeon RX 5600 XT
Recommended CPU
- Intel Core i7 7700K or above
Graphics Processing Unit
Base Clock
1607 MHz
Boost Clock
1683 MHz
Shading Units
2432
Texture Mapping Units (TMUs)
152
Render Output Units (ROPs)
64
Compute Units (Pipelines)
19
Tensor Cores
No
Ray-tracing Cores
No
L1 Cache
48KB per cluster
L2 Cache
2MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
108 GPixel/s
Texture Fill Rate
256 GTexel/s
Physical
Interface
PCIe 3.0 x16
TGP
180 W
Manufacturing
TSMC
Fabrication Process
16 nm
Die Size
314 mm²
Transistor Count
7 billion
Transistor Density
22.29 MTr/mm²
Memory
Memory Type
GDDR5
Memory Size
8 GB
Memory Clock
2002 MHz
Effective Memory Speed
8000 Mbps
Bus
256-bit
ECC
No
API
DirectX
12
Vulkan
1.3
OpenGL
4.6
OpenCL
3.0
CUDA
6.1
Ray Tracing
No
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