Radeon HD 4850 and GeForce 210 PCI - video card comparison
Radeon HD 4850
GeForce 210 PCI
Architecture
Terascale 1 (2008−2010)
Tesla 2.0 (2007−2013)
GPU code name
RV770
GT216
Market segment
Desktop
Desktop
Release date
June 2008
October 2009
Interface
PCIe 2.0 x16
PCI
Supplementary power connectors
1x 6-pin
None
Core clock speed
625 MHz
475 MHz
Floating-point performance
1,000.0 gflops
35.2 gflops
Manufacturing process technology
55 nm
40 nm
Number of transistors
956 million
486 million
Pipelines / CUDA cores
800
16
Power consumption (TDP)
110 Watt
31 Watt
Texture fill rate
25.00
3.800
Memory type
GDDR3
DDR2
Maximum RAM amount
512 MB
512 MB
Memory bus width
256 Bit
64 Bit
Memory clock speed
993 MHz
800 MHz
Memory bandwidth
63.55 GB/s
6.4 GB/s
Display Connectors
2x DVI, 1x S-Video
No outputs
DirectX
10.1 (10_1)
11.1 (10_1)
CUDA
-
1.2
OpenCL
1.1
1.1
OpenGL
3.3
3.3
Shader Model
4.1
4.1
Vulkan
N/A
N/A