GeForce RTX 3060 Ti vs Radeon HD 6990
We compared two Desktop platform GPUs: 8GB VRAM GeForce RTX 3060 Ti and 2GB VRAM Radeon HD 6990 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
GeForce RTX 3060 Ti Advantages
Released 9 years and 9 months late
Boost Clock1665MHz
More VRAM (8GB vs 2GB)
Larger VRAM bandwidth (448.0GB/s vs 160.0GB/s)
3328 additional rendering cores
Lower TDP (200W vs 375W)
Score
Benchmark
FP32 (float)
GeForce RTX 3060 Ti
+535%
16200
Radeon HD 6990
2550
Graphics Card
Dec 2020
Release Date
Mar 2011
GeForce 30
Generation
Northern Islands
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1410 MHz
Base Clock
-
1665 MHz
Boost Clock
-
1750 MHz
Memory Clock
1250 MHz
Memory
8GB
Memory Size
2GB
GDDR6
Memory Type
GDDR5
256bit
Memory Bus
256bit
448.0GB/s
Bandwidth
160.0GB/s
Render Config
-
Compute Units
24
38
SM Count
-
4864
Shading Units
1536
152
TMUs
96
80
ROPs
32
152
Tensor Cores
-
38
RT Cores
-
128 KB (per SM)
L1 Cache
8 KB (per CU)
4 MB
L2 Cache
512 KB
Theoretical Performance
133.2 GPixel/s
Pixel Rate
26.56 GPixel/s
253.1 GTexel/s
Texture Rate
79.68 GTexel/s
16.20 TFLOPS
FP16 (half)
-
16.20 TFLOPS
FP32 (float)
2.550 TFLOPS
253.1 GFLOPS
FP64 (double)
637.4 GFLOPS
Board Design
200W
TDP
375W
550 W
Suggested PSU
750 W
1x HDMI 2.1
3x DisplayPort 1.4a
3x DisplayPort 1.4a
Outputs
1x DVI
4x mini-DisplayPort 1.2
4x mini-DisplayPort 1.2
1x 12-pin
Power Connectors
2x 8-pin
Graphics Processor
GA104
GPU Name
Antilles
GA104-200-A1
GPU Variant
Antilles XT
(215-0807027)
(215-0807027)
Ampere
Architecture
TeraScale 3
Samsung
Foundry
TSMC
8 nm
Process Size
40 nm
17.4 billion
Transistors
2.64 billion
392 mm²
Die Size
389 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
11.2 (11_0)
4.6
OpenGL
4.4
3.0
OpenCL
1.2
1.3
Vulkan
N/A
8.6
CUDA
-
6.6
Shader Model
5.0