Tesla M2070 vs GeForce GTX 670

Place in the ranking	372	629
Place by popularity	not in top-100	not in top-100
Cost-effectiveness evaluation	3.38	0.10
Power efficiency	5.63	1.50
Architecture	Kepler (2012−2018)	Fermi (2010−2014)
GPU code name	GK104	GF100
Market segment	Desktop	Workstation
Release date	10 May 2012 (12 years ago)	25 July 2011 (13 years ago)
Launch price (MSRP)	$399	$3,099

Cost-effectiveness evaluation

Performance to price ratio. The higher, the better.

GTX 670 has 3280% better value for money than Tesla M2070.

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	1344	448
Core clock speed	915 MHz	574 MHz
Boost clock speed	980 MHz	no data
Number of transistors	3,540 million	3,100 million
Manufacturing process technology	28 nm	40 nm
Power consumption (TDP)	170 Watt	225 Watt
Maximum GPU temperature	97 °C	no data
Texture fill rate	109.8	32.14
Floating-point processing power	2.634 TFLOPS	1.03 TFLOPS
ROPs	32	48
TMUs	112	56

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).

Bus support	PCI Express 3.0	no data
Interface	PCIe 3.0 x16	PCIe 2.0 x16
Length	241 mm	248 mm
Height	4.376" (11.1 cm)	no data
Width	2-slot	2-slot
Supplementary power connectors	2x 6-pin	1x 6-pin + 1x 8-pin
SLI options	+	-

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	GDDR5
Maximum RAM amount	2 GB	6 GB
Memory bus width	256-bit GDDR5	384 Bit
Memory clock speed	6.0 GB/s	783 MHz
Memory bandwidth	192.2 GB/s	150.3 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	One Dual Link DVI-I, One Dual Link DVI-D, One HDMI, One DisplayPort	No outputs
Multi monitor support	4 displays	no data
HDMI	+	-
HDCP	+	-
Maximum VGA resolution	2048x1536	no data
Audio input for HDMI	Internal	no data

Supported technologies

Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.

3D Blu-Ray	+	-
3D Gaming	+	-
3D Vision	+	-

API compatibility

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

DirectX	12 (11_0)	12 (11_0)
Shader Model	5.1	5.1
OpenGL	4.2	4.6
OpenCL	1.2	1.1
Vulkan	1.1.126	N/A
CUDA	+	2.0

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	13.81	4.88
Recency	10 May 2012	25 July 2011
Maximum RAM amount	2 GB	6 GB
Chip lithography	28 nm	40 nm
Power consumption (TDP)	170 Watt	225 Watt

GTX 670 has a 183% higher aggregate performance score, an age advantage of 9 months, a 42.9% more advanced lithography process, and 32.4% lower power consumption.

Tesla M2070, on the other hand, has a 200% higher maximum VRAM amount.

The GeForce GTX 670 is our recommended choice as it beats the Tesla M2070 in performance tests.

Be aware that GeForce GTX 670 is a desktop card while Tesla M2070 is a workstation one.

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