GPUs

AMD Radeon HD 6610 vs NVIDIA GeForce RTX 4060 Ti Full Specs

400 Shaders
800MHz
4,352 Shaders
2.54GHz
1GB GDDR325.6GB/s
10GB GDDR6360GB/s
··
640 GFLOPS
··
22.11 TFLOPS
Form Factor
PCIe Card
Form Factor
PCIe Card
TDP
60W
TDP
160W
Power Connectors
-
Power Connectors
1x 16-Pin 12VHPWR

Radeon HD 6610Radeon HD 6610640 GFLOPSFP32
x1
GeForce RTX 4060 TiGeForce RTX 4060 Ti707.5 TOPSINT4 Tensor Sparse
x1105.41

Clock Speed
··
Clock Speed
···
Peak OPS
640 GFLOPSFP32
Peak OPS
707.5 TOPSINT4 Tensor Sparse
-
Tensor FP8-16
176.9 TFLOPS
FP8-16 Tensor Sparse
353.7 TFLOPS
Tensor FP8-32
88.43 TFLOPS
FP8-32 Tensor Sparse
176.9 TFLOPS
-
Tensor FP16-16
88.43 TFLOPS
FP16-16 Tensor Sparse
176.9 TFLOPS
Tensor FP16-32
44.22 TFLOPS
FP16-32 Tensor Sparse
88.43 TFLOPS
-
BF16
22.11 TFLOPS
Tensor BF16
44.22 TFLOPS
BF16 Tensor Sparse
88.43 TFLOPS
Tensor TF32
-
Tensor TF32
22.11 TFLOPS
FP32
640 GFLOPS
FP32
22.11 TFLOPS
-
FP64
345.4 GFLOPS
Tensor INT4
-
Tensor INT4
353.7 TOPS
-
Tensor INT8
176.9 TOPS
Ray
-
Ray
51.1 TOPS
Pixel Rate
6.4 GPixel/s
Pixel Rate
121.9 GPixel/s
Texture Rate
16 GTexel/s
Texture Rate
345.4 GTexel/s

Shaders
400 Shaders
Shaders
4,352 Shaders
TMUs
20 TMUs
TMUs
136 TMUs
ROPs
8 ROPs
ROPs
48 ROPs
Tensor Cores
-
Tensor Cores
136 T-Cores
RT Cores
-
RT Cores
34 RT-Cores
CUs
5 CUs
SMs
34 SMs

Base Clock
-
Base Clock
2.31GHz
Boost Clock
800MHz
Boost Clock
2.54GHz

L2 Cache
256KB shared
L2 Cache
49.1MB shared

1GB GDDR3
10GB GDDR6
Memory Bus
128-bit
Memory Bus
160-bit
Memory Speed
1.6GT/s
Memory Speed
18GT/s
Memory Bandwidth
25.6GB/s
Memory Bandwidth
360GB/s
ECC
No
ECC
No

TDP
60W
TDP
160W
Max Temp
-
Max Temp
90°C Max

Multi-Monitor
2
Multi-Monitor
4
HDCP
-
HDCP
HDCP 2.3

-
3x DisplayPort 1.4
-
1x HDMI 2.1
1x HDMI 1.3
-
1x DVI-I Dual-Link
-
1x VGA
-

-
Encoder Model
NVENC 8

Decoder Model
UVD 3.0
Decoder Model
NVDEC 5

Form Factor
PCIe Card
Form Factor
PCIe Card
PCIe
1-Slots
PCIe
2.1-Slots
-
Height
98 mm (3.86")
Width
244 mm (9.61")
Depth
42 mm (1.65")
Cooling
Open-Air
1x Fan
Cooling
Open-Air
2x Fans
Power Connectors
-
Power Connectors
1x 16-Pin 12VHPWR

Manufacturer
Manufacturer
Chip Designer
Chip Designer
Architecture
Architecture
Family
Family
Branding
Radeon 2011 branding
Branding
GeForce RTX 2022 branding
Codename
Redwood
Codename
NV186
Chip Variant
Redwood LE
Chip Variant
AD106-350-A1
Market Segment
Desktop
Market Segment
Desktop
Release Date
May 14, 2011
Release Date
May 18, 2023

Foundry
TSMC
Foundry
TSMC
Fabrication Node
40nm
Fabrication Node
4N
Die Size
104mm²
Die Size
188mm²
Transistor Count
627 Million
Transistor Count
22.9 Billion
Transistor Density
6.03 MTr/mm²
Transistor Density
121.8 MTr/mm²

No images available
No images available