Radeon HD 4850 and GeForce GT 610 PCI - video card comparison
Radeon HD 4850
GeForce GT 610 PCI
Architecture
Terascale 1 (2008−2010)
Fermi 2.0 (2010−2014)
GPU code name
RV770
GF119
Market segment
Desktop
Desktop
Release date
June 2008
April 2012
Interface
PCIe 2.0 x16
PCI
Supplementary power connectors
1x 6-pin
None
Core clock speed
625 MHz
810 MHz
Floating-point performance
1,000.0 gflops
155.5 gflops
Manufacturing process technology
55 nm
40 nm
Number of transistors
956 million
292 million
Pipelines / CUDA cores
800
48
Power consumption (TDP)
110 Watt
29 Watt
Texture fill rate
25.00
6.480
Memory type
GDDR3
DDR3
Maximum RAM amount
512 MB
512 MB
Memory bus width
256 Bit
64 Bit
Memory clock speed
993 MHz
1334 MHz
Memory bandwidth
63.55 GB/s
10.67 GB/s
Display Connectors
2x DVI, 1x S-Video
1x DVI, 1x HDMI, 1x VGA
HDMI
-
+
DirectX
10.1 (10_1)
12 (11_0)
CUDA
-
2.1
OpenCL
1.1
1.1
OpenGL
3.3
4.6
Shader Model
4.1
5.1
Vulkan
N/A
N/A