GPUs

ZOTAC GeForce RTX 3080 Ti AMP Holo vs ZOTAC GeForce RTX 3090 Trinity OC Full Specs

10,240 Shaders
1.71GHz
10,496 Shaders
1.71GHz
12GB GDDR6X936.2GB/s
24GB GDDR6X936.2GB/s
··
35.02 TFLOPS
··
35.9 TFLOPS
Form Factor
PCIe Card
Form Factor
PCIe Card
TDP
350W
TDP
350W
Power Connectors
2x 8-Pin
Power Connectors
2x 8-Pin

GeForce RTX 3080 Ti AMP HoloGeForce RTX 3080 Ti AMP Holo1.12 POPSINT4 Tensor Sparse
x1
GeForce RTX 3090 Trinity OCGeForce RTX 3090 Trinity OC1.15 POPSINT4 Tensor Sparse
x1.03

Clock Speed
···
Clock Speed
···
Peak OPS
1.12 POPSINT4 Tensor Sparse
Peak OPS
1.15 POPSINT4 Tensor Sparse
Tensor FP16-16
140.1 TFLOPS
FP16-16 Tensor Sparse
280.2 TFLOPS
Tensor FP16-32
70.04 TFLOPS
FP16-32 Tensor Sparse
140.1 TFLOPS
Tensor FP16-16
143.6 TFLOPS
FP16-16 Tensor Sparse
287.2 TFLOPS
Tensor FP16-32
71.79 TFLOPS
FP16-32 Tensor Sparse
143.6 TFLOPS
BF16
35.02 TFLOPS
Tensor BF16
70.04 TFLOPS
BF16 Tensor Sparse
140.1 TFLOPS
BF16
35.9 TFLOPS
Tensor BF16
71.79 TFLOPS
BF16 Tensor Sparse
143.6 TFLOPS
Tensor TF32
35.02 TFLOPS
Tensor TF32
35.9 TFLOPS
FP32
35.02 TFLOPS
FP32
35.9 TFLOPS
FP64
547.2 GFLOPS
FP64
560.9 GFLOPS
Tensor INT4
560.3 TOPS
Tensor INT4
574.3 TOPS
Tensor INT8
280.2 TOPS
Tensor INT8
287.2 TOPS
Ray
52.82 TOPS
Ray
54.14 TOPS
Pixel Rate
191.5 GPixel/s
Pixel Rate
191.5 GPixel/s
Texture Rate
547.2 GTexel/s
Texture Rate
560.9 GTexel/s

Shaders
10,240 Shaders
Shaders
10,496 Shaders
TMUs
320 TMUs
TMUs
328 TMUs
ROPs
112 ROPs
ROPs
112 ROPs
Tensor Cores
320 T-Cores
Tensor Cores
328 T-Cores
RT Cores
80 RT-Cores
RT Cores
82 RT-Cores
SMs
80 SMs
SMs
82 SMs

Base Clock
1.4GHz
Base Clock
1.4GHz
Boost Clock
1.71GHz
Boost Clock
1.71GHz

L2 Cache
6.1MB shared
L2 Cache
6.1MB shared

12GB GDDR6X
24GB GDDR6X
Memory Bus
384-bit
Memory Bus
384-bit
Memory Speed
19.5GT/s
Memory Speed
19.5GT/s
Memory Bandwidth
936.2GB/s
Memory Bandwidth
936.2GB/s

TDP
350W
TDP
350W
Max Temp
93°C Max
Max Temp
93°C Max

Multi-Monitor
4
Multi-Monitor
4
HDCP
HDCP 2.3
HDCP
HDCP 2.3

3x DisplayPort 1.4
3x DisplayPort 1.4
1x HDMI 2.1
1x HDMI 2.1

Encoder Model
NVENC 7
Encoder Model
NVENC 7

Decoder Model
NVDEC 5
Decoder Model
NVDEC 5

Form Factor
PCIe Card
Form Factor
PCIe Card
PCIe
3.2-Slots
PCIe
2.9-Slots
Height
131.8 mm (5.19")
Width
317.8 mm (12.51")
Depth
64.6 mm (2.54")
Height
120.7 mm (4.75")
Width
317.8 mm (12.51")
Depth
58 mm (2.28")
Cooling
Open-Air
3x Fans
Cooling
Open-Air
3x Fans
Power Connectors
2x 8-Pin
Power Connectors
2x 8-Pin

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
GeForce RTX 2018 branding
Branding
GeForce RTX 2018 branding
Codename
NV172
Codename
NV172
Chip Variant
GA102-200-KD-A1
Chip Variant
GA102-200-KD-A1
Market Segment
Desktop
Market Segment
Desktop
Release Date
Jun 3, 2021
Release Date
Sep 24, 2020

Foundry
Samsung
Foundry
Samsung
Fabrication Node
8N
Fabrication Node
8N
Die Size
628mm²
Die Size
628mm²
Transistor Count
28.3 Billion
Transistor Count
28.3 Billion
Transistor Density
45.04 MTr/mm²
Transistor Density
45.04 MTr/mm²

No images available
No images available