ATI Radeon HD 3850 vs GeForce GTX 660 OEM

Place in the ranking	734	1100
Place by popularity	not in top-100	not in top-100
Cost-effectiveness evaluation	no data	0.02
Power efficiency	1.79	0.94
Architecture	Kepler (2012−2018)	TeraScale (2005−2013)
GPU code name	GK104	RV670
Market segment	Desktop	Desktop
Release date	22 August 2012 (12 years ago)	19 November 2007 (16 years ago)
Launch price (MSRP)	no data	$179

Cost-effectiveness evaluation

Performance to price ratio. The higher, the better.

no data

Detailed specifications

General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.

Pipelines / CUDA cores	1152	320
Core clock speed	823 MHz	668 MHz
Boost clock speed	888 MHz	no data
Number of transistors	3,540 million	666 million
Manufacturing process technology	28 nm	55 nm
Power consumption (TDP)	130 Watt	75 Watt
Texture fill rate	85.25	10.69
Floating-point processing power	2.046 TFLOPS	0.4275 TFLOPS
ROPs	32	16
TMUs	96	16

Form factor & compatibility

Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).

Interface	PCIe 3.0 x16	PCIe 2.0 x16
Length	241 mm	208 mm
Width	2-slot	1-slot
Supplementary power connectors	1x 6-pin	1x 6-pin

VRAM capacity and type

Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.

Memory type	GDDR5	GDDR3
Maximum RAM amount	2 GB	1 GB
Memory bus width	256 Bit	256 Bit
Memory clock speed	1400 MHz	830 MHz
Memory bandwidth	179.2 GB/s	53.12 GB/s

Connectivity and outputs

Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.

Display Connectors	2x DVI, 1x HDMI, 1x DisplayPort	2x DVI, 1x S-Video
HDMI	+	-

API compatibility

List of supported 3D and general-purpose computing APIs, including their specific versions.

DirectX	12 (11_0)	10.1 (10_1)
Shader Model	5.1	4.1
OpenGL	4.6	3.3
OpenCL	1.2	N/A
Vulkan	1.1.126	N/A
CUDA	3.0	-

Gaming performance

Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.

Pros & cons summary

Performance score	3.36	1.02
Recency	22 August 2012	19 November 2007
Maximum RAM amount	2 GB	1 GB
Chip lithography	28 nm	55 nm
Power consumption (TDP)	130 Watt	75 Watt

GTX 660 OEM has a 229.4% higher aggregate performance score, an age advantage of 4 years, a 100% higher maximum VRAM amount, and a 96.4% more advanced lithography process.

ATI HD 3850, on the other hand, has 73.3% lower power consumption.

The GeForce GTX 660 OEM is our recommended choice as it beats the Radeon HD 3850 in performance tests.

Should you still have questions concerning choice between the reviewed GPUs, ask them in Comments section, and we shall answer.