NVIDIA GeForce 820A vs NVIDIA GeForce RTX 3060 Ti GDDR6X Comparison

NVIDIA
GEFORCE

NVIDIA GeForce 820A

CORE STATE GF117
VRAM 1024 MB
CLOCK SPEED —
TDP 15 W
BUS WIDTH 64 bit
ARCHITECTURE Fermi 2.0
nm
PROCESS 28 nm
LAUNCH DATE 2014
VS
NVIDIA
GEFORCE

GeForce RTX 3060 Ti GDDR6X

CORE STATE GA104
VRAM 8 GB
CLOCK SPEED 1665 MHz
TDP 225 W
BUS WIDTH 256 bit
ARCHITECTURE Ampere
nm
PROCESS 8 nm
LAUNCH DATE 2022

PERFORMANCE BENCHMARKS

geekbench_opencl
2,983
N/A
3dmark_3dmark_steel_nomad_dx12
N/A
2,795

Analysis: NVIDIA GeForce 820A vs NVIDIA GeForce RTX 3060 Ti GDDR6X

Where Each One Wins

The benchmark data presents an unusual pairing. The NVIDIA GeForce 820A is a legacy integrated-class part from the GeForce 800A generation, designed for low-power portability. The NVIDIA GeForce RTX 3060 Ti GDDR6X is a high-end discrete Ampere card from the GeForce 30-series. The direct head-to-head benchmark suite is empty, so the comparison relies on their respective average benchmark scores and nearest-rival relationships. The 820A's single recorded benchmark is Geekbench OpenCL, scoring 2983, while the RTX 3060 Ti's single recorded benchmark is 3DMark Steel Nomad DX12, scoring 2795. These tests are not directly comparable, but the percentile data places both in a surprisingly similar bracket: the 820A sits at the 19th percentile of all GPUs, while the RTX 3060 Ti sits at the 18th percentile.

In terms of raw compute, the RTX 3060 Ti GDDR6X is overwhelmingly dominant. Its FP32 throughput is listed at 16.20 TFLOPS, compared to the 820A's 240.0 GFLOPS. That is a difference of roughly two orders of magnitude. The RTX 3060 Ti also has 4864 shading units versus 96, 152 texture mapping units versus 16, and 80 ROPs versus 8. The 820A wins in no category of raw performance. Its only advantage is power consumption, with a 15 W TDP versus the RTX 3060 Ti's 225 W TDP, and its integrated form factor (IGP slot width) versus the RTX 3060 Ti's dual-slot design.

Where each one "wins" in a practical sense is therefore a question of context. The 820A wins in scenarios demanding minimal power draw and zero additional cooling or power connectors—it requires no external power connector, whereas the RTX 3060 Ti requires a 1x 12-pin connector and a suggested 550 W PSU. The RTX 3060 Ti wins in every performance metric relevant to gaming, rendering, or compute workloads. The data shows no benchmark wins for either in the head-to-head array, so the distinction is architectural and functional rather than demonstrated in a shared test.

Architecture Differences

The two GPUs are separated by nearly a decade of design philosophy. The 820A uses the GF117 chip, built on the Fermi 2.0 architecture, manufactured on a 28 nm process at TSMC. It packs 585 million transistors onto a 116 mm² die, yielding a transistor density of 5.0M per mm². The RTX 3060 Ti GDDR6X uses the GA104 chip, built on the Ampere architecture, manufactured on an 8 nm process at Samsung. It houses 17,400 million transistors on a 392 mm² die, for a density of 44.4M per mm². That is a massive jump in both scale and density.

Memory is another stark divider. The 820A has 1024 MB of DDR3 on a 64-bit bus, delivering 16.02 GB/s of bandwidth. The RTX 3060 Ti GDDR6X has 8 GB of GDDR6X on a 256-bit bus, delivering 608.3 GB/s. That is roughly 38 times the bandwidth. Clock speeds reflect the generational gap: the 820A's memory runs at 1001 MHz (2 Gbps effective), while the RTX 3060 Ti's memory runs at 1188 MHz (19 Gbps effective). The RTX 3060 Ti also has base and boost clocks of 1410 MHz and 1665 MHz respectively; the 820A has no listed base or boost clocks.

Feature-wise, the RTX 3060 Ti includes 38 RT cores and 152 tensor cores, enabling hardware ray tracing and AI acceleration. The 820A has no such hardware. The API support also diverges: the 820A supports DirectX 12 (11_0) and OpenGL 4.6, but no Vulkan. The RTX 3060 Ti supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The bus interface differs as well—PCIe 2.0 x16 for the 820A versus PCIe 4.0 x16 for the RTX 3060 Ti. Pixel and texture rates tell the story: 2.500 GPixel/s and 10.00 GTexel/s for the 820A, versus 133.2 GPixel/s and 253.1 GTexel/s for the RTX 3060 Ti. The RTX 3060 Ti also supports FP16 at a 1:1 ratio with FP32, while the 820A lists no FP16 capability.

Head-to-Head Benchmarks

There are no shared head-to-head benchmark entries in the data, so a direct comparison of the same test is impossible. However, the nearest-rival data provides context for each card's standing. The 820A's average benchmark score is 2983, which places it 0.5% ahead of the GTX 860M (2967), 1% ahead of the GTX 750 Ti (2953), 2.1% ahead of the Quadro P600 (2923), and 2.4% ahead of the RTX 4060 Ti 8 GB (2913). This is a peculiar grouping—the 820A is effectively trading blows with much newer and more capable parts in this particular metric, likely due to the specific workload of the Geekbench OpenCL test.

The RTX 3060 Ti GDDR6X has an average benchmark score of 2795. Its nearest rivals are the AMD Radeon 550 (2801, delta -0.2%), the NVIDIA GeForce 820M (2784, delta 0.4%), the Intel UHD Graphics 610 (2752, delta 1.6%), and the NVIDIA GeForce RTX 4010 (2893, delta -3.4%). The RTX 3060 Ti is essentially at parity with the Radeon 550, slightly ahead of the 820M and UHD 610, and 3.4% behind the RTX 4010 in this specific test. It is worth remembering the 3DMark Steel Nomad DX12 test is a modern, demanding workload, so the RTX 3060 Ti's score of 2795 is not representative of its overall capability in less strenuous tasks.

The biggest wins each way are not in the head-to-head array but in the architectural specs. The RTX 3060 Ti wins decisively on FP32 (16.20 TFLOPS vs 240.0 GFLOPS), memory bandwidth (608.3 GB/s vs 16.02 GB/s), and texture rate (253.1 GTexel/s vs 10.00 GTexel/s). The 820A wins on TDP (15 W vs 225 W) and power connector requirements (none vs 1x 12-pin). These are the only clear victories for the 820A.

FAQ

Q: Which GPU has more shading units?

A: The RTX 3060 Ti GDDR6X has 4864 shading units, while the 820A has only 96.

Q: What is the memory bandwidth of each card?

A: The 820A has 16.02 GB/s of bandwidth from 1 GB of DDR3 on a 64-bit bus. The RTX 3060 Ti GDDR6X has 608.3 GB/s from 8 GB of GDDR6X on a 256-bit bus.

Q: Does the 820A support ray tracing?

A: No. The 820A has no RT cores or tensor cores. The RTX 3060 Ti GDDR6X has 38 RT cores and 152 tensor cores.

Q: Which card has a lower power draw?

A: The 820A has a 15 W TDP and requires no power connector. The RTX 3060 Ti GDDR6X has a 225 W TDP and requires a 1x 12-pin power connector, with a suggested 550 W PSU.

Q: How do their average benchmark scores compare?

A: The 820A scores 2983 in its single Geekbench OpenCL test, placing it at the 19th percentile. The RTX 3060 Ti GDDR6X scores 2795 in its single 3DMark Steel Nomad DX12 test, placing it at the 18th percentile. These are different tests, so the scores are not directly comparable.

Q: What API support does each card offer?

A: The 820A supports DirectX 12 (11_0) and OpenGL 4.6, but no Vulkan. The RTX 3060 Ti GDDR6X supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The Verdict

The data is unambiguous on performance: the RTX 3060 Ti GDDR6X is the superior GPU in every computational metric. It has over 50 times the FP32 throughput, 38 times the memory bandwidth, and 25 times the shading units. It also brings modern features like ray tracing, tensor cores, and Vulkan support, none of which exist on the 820A. Anyone looking for gaming, rendering, or compute capability should choose the RTX 3060 Ti GDDR6X without hesitation.

The 820A, however, is not without a niche. Its 15 W TDP, IGP form factor, and lack of external power connectors make it suitable for ultra-low-power systems or embedded applications where performance is secondary to energy efficiency. It is an end-of-life product from the GeForce 800A generation, succeeded by the GeForce 900A, and its nearest rivals include the GTX 860M and GTX 750 Ti—parts that are also dated. The benchmark data shows it performs comparably to those older parts in OpenCL, but that is a narrow window.

The RTX 3060 Ti GDDR6X, also end-of-life, sits in the GeForce 30-series and was succeeded by the GeForce 40-series. Its nearest rivals in the 3DMark Steel Nomad DX12 test include the AMD Radeon 550 and the Intel UHD Graphics 610, which are far less capable cards—a reminder that this specific benchmark score is not indicative of the RTX 3060 Ti's real-world standing. In absolute terms, the RTX 3060 Ti is the clear choice for any workload that can use its compute resources. The 820A is only viable where power and physical footprint are the overriding constraints.

DETAILED SPECIFICATIONS

SPECIFICATION
820A
RTX 3060 Ti GDDR6X
Core Specs
Shading Units
96
4,864 +4966.7%
Shaders
96
4,864 +4966.7%
TMUs
16
152 +850.0%
ROPs
8
80 +900.0%
SM Count
2
38 +1800.0%
Clocks
Base Clock
—
1410 MHz
Boost Clock
—
1665 MHz
GPU Clock
625 MHz
—
Shader Clock
1250 MHz
—
Memory Clock
1001 MHz 2 Gbps effective
1188 MHz 19 Gbps effective
Memory
Memory Size
1024 MB
8 GB
VRAM (MB)
1,024
8,192 +700.0%
Memory Type
DDR3
GDDR6X
Memory Bus
64 bit
256 bit
Bandwidth
16.02 GB/s
608.3 GB/s
Cache
L1 Cache
64 KB (per SM)
128 KB (per SM)
L2 Cache
128 KB
4 MB
Performance
Pixel Rate
2.500 GPixel/s
133.2 GPixel/s
Texture Rate
10.00 GTexel/s
253.1 GTexel/s
FP32 (TFLOPS)
240.0 GFLOPS
16.20 TFLOPS
FP64 (TFLOPS)
20.00 GFLOPS (1:12)
253.1 GFLOPS (1:64)
FP16 (TFLOPS)
—
16.20 TFLOPS (1:1)
AI/RT
RT Cores
—
38
Tensor Cores
—
152
Power
TDP
15 W
225 W
TDP (W)
15
225 +1400.0%
Suggested PSU
—
550 W
Power Connectors
None
1x 12-pin
Architecture
Architecture
Fermi 2.0
Ampere
GPU Name
GF117
GA104
Generation
GeForce 800A
GeForce 30
Process Size
28 nm
8 nm
Transistors
585 million
17,400 million
Die Size
116 mm²
392 mm²
Foundry
TSMC
Samsung
Density
5.0M / mm²
44.4M / mm²
API Support
DirectX
12 (11_0)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
—
1.4
OpenCL
1.1
3.0
CUDA
2.1
8.6
Shader Model
5.1
6.8
Physical
Slot Width
IGP
Dual-slot
Length
—
242 mm 9.5 inches
Height
—
112 mm 4.4 inches
Outputs
Portable Device Dependent
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
PCIe 2.0 x16
PCIe 4.0 x16
Other
Production
End-of-life
End-of-life
Predecessor
GeForce 700A
GeForce 20
Successor
GeForce 900A
GeForce 40
View GeForce 820A Details View GeForce RTX 3060 Ti GDDR6X Details