NVIDIA GeForce GTX 670 vs NVIDIA GeForce RTX 3080 Ti 20 GB

GPU · Specs Compare

Products
GPU NVIDIA GeForce GTX 670 NVIDIA · 2012-05
GPU NVIDIA GeForce RTX 3080 Ti 20 GB NVIDIA · 2025-06
Graphics Card
Release Date
May 2012
Jun 2025
Generation
GeForce 600
Navi IV
Type
Desktop
Desktop
Bus Interface
PCIe 3.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
915 MHz
1700 MHz
Boost Clock
980 MHz
3130 MHz
Memory Clock
1502 MHz
2518 MHz
Memory
Memory Size
2GB
8GB
Memory Type
GDDR5
GDDR6
Memory Bus
256bit
128bit
Bandwidth
192.3GB/s
322.3GB/s
Render Config
Shading Units
1344
2048
TMUs
112
128
ROPs
32
64
L1 Cache
16 KB (per SMX)
128 KB (per SM)
L2 Cache
512 KB
4 MB
SM Count
—
80
Compute Units
—
32
Tensor Cores
—
320
RT Cores
—
32
L3 Cache
—
32 MB
Theoretical Performance
Pixel Rate
27.44 GPixel/s
200.3 GPixel/s
Texture Rate
109.8 GTexel/s
400.6 GTexel/s
FP32 (float)
2.634 TFLOPS
25.64 TFLOPS
FP64 (double)
109.8 GFLOPS
801.3 GFLOPS
FP16 (half)
—
51.28 TFLOPS
Graphics Processor
GPU Name
GK104
Navi 44
GPU Variant
GK104-325-A2
Navi 44 XT(215-176400102)
Architecture
Kepler
RDNA 4.0
Foundry
TSMC
TSMC
Process Size
28 nm
4 nm
Transistors
3.54 billion
29.7 billion
Die Size
294 mm²
199 mm²
Board Design
TDP
170W
150W
Suggested PSU
450 W
450 W
Outputs
2x DVI1x HDMI 1.4a1x DisplayPort 1.2
1x HDMI 2.1b2x DisplayPort 2.1a
Power Connectors
2x 6-pin
1x 8-pin
Graphics Features
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
2.2
Vulkan
1.1
1.3
CUDA
3.0
8.6
Shader Model
5.1
6.8
Benchmark
Blender
—
5,956
▲ Specs Compare Data sourced from official specifications and benchmark tests.