GeForce RTX 3070 Ti
46B
Memory8 GB
Memory TypeGDDR6X
Boost Clock1770 MHz
TGP290 W
ArchitectureAmpere
Launch Price$599
Benchmarks
Gaming47
Render49
TFLOPS (FP32)21.7
Geekbench OpenCL136,096
3DMarkTime Spy14,881
Steel Nomad Lite Score15,393
GB6 Compute Score136,096
Cinebench 2024 GPU11,990
G3D Mark Score23,173
Blender GPU3732.22
GB6 ML Single Precision22,516
GB6 ML Half Precision36,377
GB6 ML Quantized14,215
FLOPS (FP32)21.7 TFLOPS
Memory Bandwidth608.3 GB/s
Full specifications
3D Mark
Time Spy
14881
Solar Bay
69901
Port Royal
8884
Fire Strike
37242
Wild Life Extreme
31912
Night Raid
134068
GeekBench 6 OpenCL
Background Blur
197 img/sec
Face Detection
128.1 img/sec
Horizon Detection
6.56 Gpixels/sec
Edge Detection
8.81 Gpixels/sec
Gaussian Blur
6.47 Gpixels/sec
Feature Matching
1.26 Gpixels/sec
Stereo Matching
609.3 Gpixels/sec
Particle Physics
18205 FPS
API
OpenCL
Passmark Graphics
G2D Mark
1057
DirectX 11
192 FPS
DirectX 12
90 FPS
GPU Compute
11384 Ops/s
GeekBench 6 ML
Image Classification (SP)
8615
Image Segmentation (HP)
24659
Image Super Resolution (Q)
20631
Face Detection (HP)
43834
Pose Estimation (Q)
98347
Text Classification (SP)
3162
Machine Translation (HP)
4911
Object Detection (SP)
11498
Depth Estimation (Q)
34719
Style Transfer (SP)
196833
Framework
ONNX
Backend
DirectML
General
Vendor
Nvidia
Build
Discrete
Released
June 10, 2021
Launch price (MSRP)
$599
Case
Desktop
Purpose
Gaming
Segment
Mid-range
Architecture
Ampere
GPU Codename
GA104
AMD Equivalent
- Radeon RX 7800 XT
Successor
- GeForce RTX 5070 Ti
Recommended CPU
- Intel Core i7 12700K or above
Graphics Processing Unit
Base Clock
1575 MHz
Boost Clock
1770 MHz
Shading Units
6144
Texture Mapping Units (TMUs)
192
Render Output Units (ROPs)
96
Compute Units (Pipelines)
48
Tensor Cores
192
Ray-tracing Cores
48
L1 Cache
128KB per cluster
L2 Cache
4MB shared
Instructions Per Cycle
2 IPC
Raw Performance
Pixel Fill Rate
170 GPixel/s
Texture Fill Rate
340 GTexel/s
Physical
Interface
PCIe 4.0 x16
TGP
290 W
Manufacturing
Samsung
Fabrication Process
8 nm
Die Size
392 mm²
Transistor Count
17 billion
Transistor Density
43.37 MTr/mm²
Memory
Memory Type
GDDR6X
Memory Size
8 GB
Memory Clock
1188 MHz
Effective Memory Speed
19000 Mbps
Bus
256-bit
ECC
No
API
DirectX
12
Vulkan
1.3
OpenGL
4.6
OpenCL
3.0
CUDA
8.6
Ray Tracing
Yes
DLSS
DLSS 2
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