Report an Error

NVIDIA A2

Graphics Processor
GA107
Cores
1280
TMUs
40
ROPs
32
Memory Size
16 GB
Memory Type
GDDR6
Bus Width
128 bit
GPU Chip
GPU
The A2 is a professional graphics card by NVIDIA, launched on November 10th, 2021. Built on the 8 nm process, and based on the GA107 graphics processor, the card supports DirectX 12 Ultimate. The GA107 graphics processor is an average sized chip with a die area of 200 mm² and 8,700 million transistors. Unlike the fully unlocked GeForce RTX 3050 8 GB GA107, which uses the same GPU but has all 2560 shaders enabled, NVIDIA has disabled some shading units on the A2 to reach the product's target shader count. It features 1280 shading units, 40 texture mapping units, and 32 ROPs. Also included are 40 tensor cores which help improve the speed of machine learning applications. The card also has 10 raytracing acceleration cores. NVIDIA has paired 16 GB GDDR6 memory with the A2, which are connected using a 128-bit memory interface. The GPU is operating at a frequency of 1440 MHz, which can be boosted up to 1770 MHz, memory is running at 1563 MHz (12.5 Gbps effective).
Being a single-slot card, the NVIDIA A2 does not require any additional power connector, its power draw is rated at 60 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. A2 is connected to the rest of the system using a PCI-Express 4.0 x8 interface.

Graphics Processor

GPU Name
GA107
Architecture
Ampere
Foundry
Samsung
Process Size
8 nm
Transistors
8,700 million
Density
43.5M / mm²
Die Size
200 mm²
Chip Package
FCBGA-1358

Graphics Card

Release Date
Nov 10th, 2021
Generation
Workstation Ampere
(Ax000)
Predecessor
Quadro Turing
Successor
Workstation Ada
Production
Active
Bus Interface
PCIe 4.0 x8

Relative Performance

GeForce RTX 5090
1559%
GeForce RTX 4090
1189%
GeForce RTX 5080
1027%
GeForce RTX 4080 SUPER
917%
GeForce RTX 4080
909%
Radeon RX 7900 XTX
909%
GeForce RTX 5070 Ti
896%
Radeon RX 9070 XT
856%
Radeon RX 7900 XT
783%
GeForce RTX 3090 Ti
768%
GeForce RTX 4070 Ti SUPER
768%
Radeon RX 9070
767%
GeForce RTX 4070 Ti
703%
GeForce RTX 5070
696%
GeForce RTX 3090
685%
GeForce RTX 3080 Ti
676%
GeForce RTX 4070 SUPER
655%
Radeon RX 7900 GRE
645%
Radeon RX 6950 XT
634%
GeForce RTX 4070
625%
Radeon RX 6900 XT
619%
GeForce RTX 3080
609%
Radeon RX 7800 XT
607%
Radeon RX 6800 XT
586%
GeForce RTX 5060 Ti 16 GB
544%
GeForce RTX 5060 Ti 8 GB
541%
Radeon RX 7700 XT
533%
Radeon RX 9060 XT 16 GB
516%
GeForce RTX 3070 Ti
515%
Radeon RX 6800
498%
Radeon RX 6750 XT
494%
Radeon RX 9060 XT 8 GB
487%
GeForce RTX 3070
482%
GeForce RTX 2080 Ti
478%
GeForce RTX 4060 Ti 8 GB
476%
GeForce RTX 5060
469%
GeForce RTX 3060 Ti
422%
Radeon RX 6700 XT
415%
GeForce RTX 2080 SUPER
385%
Radeon RX 7600 XT
382%
GeForce RTX 4060
381%
Arc B580
380%
GeForce RTX 5050
370%
GeForce RTX 2080
367%
Radeon RX 6650 XT
359%
Radeon RX 7600
359%
GeForce RTX 2070 SUPER
342%
GeForce GTX 1080 Ti
338%
Arc A770
338%
GeForce RTX 3060 12 GB
325%
Radeon RX 6600 XT
321%
Radeon VII
320%
Arc A750
313%
Radeon RX 5700 XT
306%
GeForce RTX 2070
302%
Radeon RX 6600
288%
Arc A580
280%
GeForce RTX 2060 SUPER
280%
Radeon RX Vega 64
268%
GeForce RTX 2060
259%
Radeon RX 5700
258%
GeForce GTX 1080
253%
GeForce GTX 1070 Ti
248%
Radeon RX 5600 XT
246%
Radeon RX Vega 56
234%
GeForce GTX 1070
225%
GeForce GTX 1660 SUPER
213%
GeForce GTX 1660 Ti
213%
GeForce GTX 980 Ti
202%
GeForce RTX 3050 8 GB
201%
Radeon R9 FURY X
198%
GeForce GTX 1660
196%
Radeon RX 590
185%
Radeon R9 FURY
181%
GeForce GTX 980
178%
GeForce GTX 1650 SUPER
177%
Radeon RX 6500 XT
174%
Radeon RX 5500 XT
173%
Radeon RX 580
172%
GeForce GTX 1060 6 GB
167%
Radeon R9 390X
165%
GeForce GTX 690
163%
Radeon RX 480
161%
Radeon HD 7990
161%
GeForce GTX 780 Ti
158%
GeForce GTX 970
154%
Radeon R9 290X
153%
Radeon R9 390
151%
Radeon RX 570
149%
Radeon R9 290
141%
Radeon RX 470
139%
GeForce GTX 1650
131%
Radeon RX 6400
129%
Arc A380
127%
GeForce GTX 780
127%
Radeon HD 7970 GHz Edition
114%
GeForce GTX 590
114%
Radeon R9 280X
113%
Radeon HD 6990
110%
GeForce GTX 1050 Ti
105%
GeForce GTX 680
102%
Radeon R9 380
101%
Radeon HD 7970
101%
GeForce GTX 770
101%
Radeon R9 285
100%
A2
100%
GeForce GTX 960
97%
GeForce GTX 670
95%
Radeon HD 5970
86%
GeForce GTX 1630
86%
Radeon HD 7950
84%
GeForce GTX 1050
84%
GeForce GTX 760
83%
GeForce GTX 580
83%
GeForce GTX 660 Ti
83%
Radeon R9 270X
82%
Radeon HD 7870 GHz Edition
80%
GeForce GTX 950
79%
Radeon RX 560
75%
GeForce GTX 570
73%
GeForce GTX 660
73%
Radeon RX 460
73%
Radeon R7 370
73%
Radeon HD 6970
70%
GeForce GTX 480
67%
Radeon HD 7850
66%
GeForce GTX 295
65%
Radeon HD 6950
63%
GeForce GTX 750 Ti
62%
Radeon HD 4870 X2
61%
GeForce GTX 560 Ti
61%
Radeon HD 5870
59%
Radeon HD 6870
55%
GeForce GTX 470
53%
GeForce GTX 650 Ti
51%
Radeon HD 5850
50%
GeForce GTX 285
47%
Radeon HD 6850
46%
GeForce GTX 280
43%
Radeon HD 7770 GHz Edition
43%
GeForce GTX 275
43%
GeForce GT 1030
42%
GeForce GTX 460
42%
Radeon HD 4890
40%
Radeon HD 6790
39%
Radeon HD 5830
38%
GeForce GTX 650
35%
GeForce GTX 550 Ti
35%
Radeon HD 4870
35%
GeForce GTX 260
34%
Radeon HD 5770
34%
Radeon HD 7750
33%
Radeon HD 5750
29%
GeForce GTS 450
28%
GeForce GTS 250
27%
Radeon HD 4850
27%
Radeon HD 4770
25%
Radeon HD 4830
24%
Radeon HD 6670
23%
GeForce 9800 GT
22%
GeForce GT 640
22%
Radeon HD 5670
20%
GeForce 9600 GT
19%
GeForce GT 240
16%
GeForce GT 440
16%
Radeon HD 4670
15%
Radeon HD 5570
14%
GeForce GT 430
14%
GeForce GT 220
11%
GeForce GT 520
9%
Radeon HD 6450
8%
Radeon HD 5450
7%
Radeon HD 4550
5%
GeForce 9400 GT
4%
GeForce 210
3%
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for RTX 3080 and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

Base Clock
1440 MHz
Boost Clock
1770 MHz
Memory Clock
1563 MHz
12.5 Gbps effective

Memory

Memory Size
16 GB
Memory Type
GDDR6
Memory Bus
128 bit
Bandwidth
200.1 GB/s

Render Config

Shading Units
1280
TMUs
40
ROPs
32
SM Count
10
Tensor Cores
40
RT Cores
10
L1 Cache
128 KB (per SM)
L2 Cache
2 MB

Theoretical Performance

Pixel Rate
56.64 GPixel/s
Texture Rate
70.80 GTexel/s
FP16 (half)
4.531 TFLOPS (1:1)
FP32 (float)
4.531 TFLOPS
FP64 (double)
70.80 GFLOPS (1:64)

Board Design

Slot Width
Single-slot
TDP
60 W
Suggested PSU
250 W
Outputs
No outputs
Power Connectors
None
Board Number
PG179 SKU 220

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
8.6
Shader Model
6.8

GA107 GPU Notes

Ray Tracing Cores: 2nd Gen
Tensor Cores: 3rd Gen
NVENC: 7th Gen
NVDEC: 5th Gen
PureVideo HD: VP11
VDPAU: Feature Set K

Latest Drivers:
Windows 7 / 8 / 8.1 (x64):
GeForce Release 474.89

Windows 10 / 11 (x64):
GeForce Release: Latest
Quadro Release: Latest
Data Center Release: Latest
Jul 15th, 2025 22:16 CDT change timezone

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts