GIGABYTE GeForce RTX 3090 Ti Gaming OC vs NVIDIA GeForce RTX 2060 TU104
GIGABYTE GeForce RTX 3090 Ti Gaming OC
$1,999
NVIDIA GeForce RTX 2060 TU104
$299
|
10752 Shaders
24GB GDDR6X
1905MHz
|
1920 Shaders
6GB GDDR6
1680MHz
|
|
Peak AI Performance
1.31 POPS
INT4 Tensor Sparse
|
Peak AI Performance
206.44 TOPS
INT4 Tensor
|
|
FP32
40.97 TFLOPS
|
FP32
6.45 TFLOPS
|
|
FP16
40.97 TFLOPS
|
FP16
12.9 TFLOPS
|
|
Form Factor
PCIe Card
3.4-Slots
|
Form Factor
PCIe Card
2.0-Slots
|
|
TDP
450W
|
TDP
160W
|
|
Power Connectors
-
-
-
1x 16-Pin 12VHPWR
|
Power Connectors
-
1x 8-Pin
-
-
|
|
GB6 OpenCL N/A
0%
|
GB6 OpenCL N/A
0%
|
|
GB6 Metal N/A
0%
|
GB6 Metal N/A
0%
|
|
GB6 Vulkan N/A
0%
|
GB6 Vulkan N/A
0%
|
|
GB5 OpenCL 230,890
76%
|
GB5 OpenCL 70,345
23%
|
|
GB5 CUDA 268,250
76%
|
GB5 CUDA 77,810
22%
|
|
GB5 Metal N/A
0%
|
GB5 Metal N/A
0%
|
|
GB5 Vulkan 155,325
76%
|
GB5 Vulkan 60,540
29%
|
|
OCT 2020.1 755
99%
|
OCT 2020.1 190
25%
|
|
OCT Metal N/A
0%
|
OCT Metal N/A
0%
|
|
Peak AI
Performance
1.31 POPS
INT4 Tensor Sparse
|
Peak AI
Performance
206.44 TOPS
INT4 Tensor
|
|
-
-
-
|
-
-
-
|
|
-
-
-
-
-
-
|
-
-
-
-
-
-
|
|
FP16
40.97 TFLOPS
163.86 TFLOPS
Tensor (FP16 Accumulate)
327.72 TFLOPS
Tensor (FP16 Accumulate) Sparse
81.93 TFLOPS
Tensor (FP32 Accumulate)
163.86 TFLOPS
Tensor (FP32 Accumulate) Sparse
|
FP16
12.9 TFLOPS
51.61 TFLOPS
Tensor (FP16 Accumulate)
-
25.81 TFLOPS
Tensor (FP32 Accumulate)
-
|
|
FP32
40.97 TFLOPS
-
-
|
FP32
6.45 TFLOPS
-
-
|
|
FP64
640 GFLOPS
-
|
FP64
200 GFLOPS
-
|
|
BF16
40.97 TFLOPS
81.93 TFLOPS
Tensor
163.86 TFLOPS
Tensor Sparse
|
BF16
-
25.81 TFLOPS
Tensor
-
|
|
TF32
40.97 TFLOPS
Tensor
81.93 TFLOPS
Tensor Sparse
|
TF32
25.81 TFLOPS
Tensor
-
|
|
INT4
655.44 TOPS
Tensor
1.31 POPS
Tensor Sparse
|
INT4
206.44 TOPS
Tensor
-
|
|
INT8
-
327.72 TOPS
Tensor
655.44 TOPS
Tensor Sparse
|
INT8
-
103.22 TOPS
Tensor
-
|
|
INT32
20.48 TOPS
|
INT32
6.45 TOPS
|
|
Ray Tracing
80 TOPS
|
Ray Tracing
19.5 TOPS
|
|
Pixel
Fillrate
213.36 GPixel/s
|
Pixel
Fillrate
80.64 GPixel/s
|
|
-
-
|
-
-
|
|
Texture
Fillrate
640.08 GTexel/s
|
Texture
Fillrate
201.6 GTexel/s
|
|
Manufacturer
GIGABYTE
|
Manufacturer
NVIDIA
|
|
Chip Designer
NVIDIA
|
Chip Designer
NVIDIA
|
|
Architecture
Ampere
|
Architecture
Turing
|
|
Family
GeForce 30
|
Family
GeForce 20
|
|
Codename
NV172
GA102
Variant
GA102-350-A1
|
Codename
NV164
TU104
Variant
TU104-150-KC-A1
|
|
Market Segment
Desktop
|
Market Segment
Desktop
|
|
Release Date
3/29/2022
|
Release Date
1/10/2020
|
|
Foundry
Samsung
-
|
Foundry
TSMC
-
|
|
Fabrication Node
8N
-
|
Fabrication Node
12FFN
-
|
|
Die Size
628 mm²
-
|
Die Size
545 mm²
-
|
|
Transistor Count
28.3 Billion
-
|
Transistor Count
13.6 Billion
-
|
|
Transistor Density
45.04M/mm²
-
|
Transistor Density
24.95M/mm²
-
|
|
Form
PCIe Card
|
Form
PCIe Card
|
|
Shading Units
10752 Shaders
-
|
Shading Units
1920 Shaders
-
|
|
Texture Mapping Units
336 TMUs
|
Texture Mapping Units
120 TMUs
|
|
Render Output Units
112 ROPs
|
Render Output Units
48 ROPs
|
|
Tensor Cores
336 T-Cores
|
Tensor Cores
240 T-Cores
|
|
Ray-Tracing Cores
84 RT-Cores
|
Ray-Tracing Cores
30 RT-Cores
|
|
Streaming Multiprocessors
84 SMs
|
Streaming Multiprocessors
30 SMs
|
|
-
-
|
-
-
|
|
-
-
|
-
-
|
|
Graphics Processing Clusters
7 GPCs
|
Graphics Processing Clusters
3 GPCs
|
|
-
-
1560MHz Base
1905MHz
|
-
-
1365MHz Base
1680MHz
|
|
-
-
|
-
-
|
|
L1
64KB/SM Tex
128KB/SM
-
-
|
L1
32KB/SM Tex
64KB/SM
-
-
|
|
L2
6MB Shared
|
L2
4MB Shared
|
|
-
-
-
|
-
-
-
|
|
24GB
GDDR6X
-
|
6GB
GDDR6
-
|
|
Bus Width
384Bit
|
Bus Width
192Bit
|
|
Clock
1313MHz
Transfer Rate
21GT/s
Bandwidth
1008GB/s
|
Clock
1750MHz
Transfer Rate
14GT/s
Bandwidth
336GB/s
|
|
-
-
-
-
-
-
-
-
-
|
-
-
-
-
-
-
-
-
-
|
|
TDP
450W
|
TDP
160W
|
|
Temp
92°C Max
|
Temp
88°C Max
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
3x DisplayPort 1.4
-
-
-
-
-
-
-
-
-
-
-
1x HDMI 2.1
-
-
|
-
-
-
-
-
-
-
-
-
-
1x DVI-D Dual-Link
-
-
-
-
-
-
-
-
-
-
-
-
-
3x DisplayPort 1.4
-
-
-
-
-
-
-
-
-
-
1x HDMI 2.0
-
1x USB-C + DP
-
|
|
Max Resolution
7680x4320
|
Max Resolution
7680x4320
|
|
Max Resolution Refresh Rate
60Hz
|
Max Resolution Refresh Rate
60Hz
|
|
Variable Refresh Rate
G-Sync
FreeSync
-
|
Variable Refresh Rate
G-Sync
FreeSync
-
|
|
Display Stream Compression (DSC)
Supported
|
Display Stream Compression (DSC)
Supported
|
|
Multi Monitor Support
4
|
Multi Monitor Support
4
|
|
Content Protection
HDCP 2.3
|
Content Protection
HDCP 2.2
|
|
Model
NVENC 7
|
Model
NVENC 7
|
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
|
Model
NVDEC 5
|
Model
NVDEC 4
|
|
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
|
|
Direct X
12
Direct 3D
12_2
|
Direct X
12
Direct 3D
12_2
|
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2
|
|
Shader Model
6.6
CUDA
8.6
-
-
PureVideo HD
VP11
VDPAU
Feature Set K
|
Shader Model
6.6
CUDA
7.5
-
-
PureVideo HD
VP10
VDPAU
Feature Set J
|
|
-
-
-
3x Fans
|
-
-
-
2x Fans
|
|
Power Connectors
-
-
-
-
-
-
1x 16-Pin 12VHPWR
|
Power Connectors
-
-
-
1x 8-Pin
-
-
-
|
|
Slots Required
3.4
PCIe Version
4.0
PCIe Lanes
16
|
Slots Required
2.0
PCIe Version
3.0
PCIe Lanes
16
|
|
Multi GPU Support
Supported
Type
2-way NVLink
|
-
-
-
-
|
|
Height
150 mm (5.91 in)
Width
331 mm (13.03 in)
Depth
70 mm (2.76 in)
|
Height
112.6 mm (4.43 in)
Width
228.6 mm (9 in)
Depth
35 mm (1.38 in)
|
Copy Link