GPUs

NVIDIA A2 vs GIGABYTE GeForce RTX 3050 OC Low Profile 6G Full Specs

1,280 Shaders
1.77GHz
2,304 Shaders
1.48GHz
16GB GDDR6100.1GB/s
6GB GDDR6168GB/s
··
4.53 TFLOPS
··
6.81 TFLOPS
Form Factor
PCIe Card
Form Factor
PCIe Card
TDP
60W
TDP
70W

A2A2145 TOPSINT4 Tensor Sparse
x1
GeForce RTX 3050 OC Low Profile 6GGeForce RTX 3050 OC Low Profile 6G217.8 TOPSINT4 Tensor Sparse
x1.50

Clock Speed
···
Clock Speed
···
Peak OPS
145 TOPSINT4 Tensor Sparse
Peak OPS
217.8 TOPSINT4 Tensor Sparse
Tensor FP16-16
18.12 TFLOPS
FP16-16 Tensor Sparse
36.25 TFLOPS
Tensor FP16-32
9.06 TFLOPS
FP16-32 Tensor Sparse
18.12 TFLOPS
Tensor FP16-16
27.22 TFLOPS
FP16-16 Tensor Sparse
54.45 TFLOPS
Tensor FP16-32
13.61 TFLOPS
FP16-32 Tensor Sparse
27.22 TFLOPS
BF16
4.53 TFLOPS
Tensor BF16
9.06 TFLOPS
BF16 Tensor Sparse
18.12 TFLOPS
BF16
6.81 TFLOPS
Tensor BF16
13.61 TFLOPS
BF16 Tensor Sparse
27.22 TFLOPS
Tensor TF32
4.53 TFLOPS
Tensor TF32
6.81 TFLOPS
FP32
4.53 TFLOPS
FP32
6.81 TFLOPS
FP64
70.8 GFLOPS
FP64
106.3 GFLOPS
Tensor INT4
72.5 TOPS
Tensor INT4
108.9 TOPS
Tensor INT8
36.25 TOPS
Tensor INT8
54.45 TOPS
Ray
6.83 TOPS
Ray
10.26 TOPS
Pixel Rate
56.6 GPixel/s
Pixel Rate
47.3 GPixel/s
Texture Rate
70.8 GTexel/s
Texture Rate
106.3 GTexel/s

Shaders
1,280 Shaders
Shaders
2,304 Shaders
TMUs
40 TMUs
TMUs
72 TMUs
ROPs
32 ROPs
ROPs
32 ROPs
Tensor Cores
40 T-Cores
Tensor Cores
72 T-Cores
RT Cores
10 RT-Cores
RT Cores
18 RT-Cores
SMs
10 SMs
SMs
18 SMs

Base Clock
1.44GHz
Base Clock
1.04GHz
Boost Clock
1.77GHz
Boost Clock
1.48GHz

L2 Cache
2MB shared
L2 Cache
2MB shared

16GB GDDR6
6GB GDDR6
Memory Bus
128-bit
Memory Bus
96-bit
Memory Speed
6.3GT/s
Memory Speed
14GT/s
Memory Bandwidth
100.1GB/s
Memory Bandwidth
168GB/s

TDP
60W
TDP
70W

Multi-Monitor
-
Multi-Monitor
3
HDCP
-
HDCP
HDCP 2.3

-
2x DisplayPort 1.4
-
2x 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
1-Slots
PCIe
1.8-Slots
Height
69 mm (2.72")
Width
168 mm (6.61")
Depth
20 mm (0.79")
Height
69 mm (2.72")
Width
181 mm (7.13")
Depth
36 mm (1.42")
Cooling
Passive
-
Cooling
Open-Air
2x Fans

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
A2 branding
Branding
GeForce RTX 2018 branding
Codename
NV177
Codename
NV177
Chip Variant
GA107-140-A1
Chip Variant
GA107-140-A1
Market Segment
Server
Market Segment
Desktop
Release Date
Nov 10, 2021
Release Date
Feb 2, 2024

Foundry
Samsung
Foundry
Samsung
Fabrication Node
8N
Fabrication Node
8N
Die Size
200mm²
Die Size
200mm²
Transistor Count
8.7 Billion
Transistor Count
8.7 Billion
Transistor Density
43.5 MTr/mm²
Transistor Density
43.5 MTr/mm²

No images available
No images available