GeForce GTX 670: specs and benchmarks
Aggregate performance score
GeForce GTX 670 provides acceptable gaming and benchmark performance at 12.63% of a leader's which is GeForce RTX 5090 D.
Contents
Summary
NVIDIA started GeForce GTX 670 sales 10 May 2012 at a recommended price of $399. This is a desktop graphics card based on a Kepler architecture and made with 28 nm manufacturing process. It is primarily aimed at gamer market. 2 GB of GDDR5 memory clocked at 6.0 GB/s are supplied, and together with 256-bit GDDR5 memory interface this creates a bandwidth of 192.2 GB/s.
Compatibility-wise, this is a dual-slot graphics card attached via PCIe 3.0 x16 interface. Its manufacturer default version has a length of 241 mm. Two 6-pin power connectors are required, and power consumption is at 170 Watt.
Primary details
Some basic facts about GeForce GTX 670: architecture, market segment, release date etc.
| Place in the ranking | 410 | |
| Place by popularity | not in top-100 | |
| Cost-effectiveness evaluation | 2.91 | |
| Power efficiency | 5.66 | of 100.00 (Radeon 890M) |
| Architecture | Kepler (2012−2018) | |
| GPU code name | GK104 | |
| Market segment | Desktop | |
| Release date | 10 May 2012 (13 years ago) | |
| Launch price (MSRP) | $399 | of 14,999 (Quadro Plex 7000) |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices for comparison.
Performance to price scatter graph
Detailed specifications
GeForce GTX 670's specs such as number of shaders, GPU base clock, manufacturing process, texturing and calculation speed. These parameters indirectly speak of GeForce GTX 670's performance, but for precise assessment you have to consider its benchmark and gaming test results.
| Pipelines / CUDA cores | 1344 | of 24064 (RTX PRO 6000 Blackwell) |
| Core clock speed | 915 MHz | of 2670 MHz (Arc B580) |
| Boost clock speed | 980 MHz | of 3230 MHz (Radeon RX 9060 XT) |
| Number of transistors | 3,540 million | of 185,000 million (Radeon Instinct MI350X) |
| Manufacturing process technology | 28 nm | of 3 nm (Arc Graphics 140V) |
| Power consumption (TDP) | 170 Watt | of 2400 Watt (Data Center GPU Max Subsystem) |
| Maximum GPU temperature | 97 °C | |
| Texture fill rate | 109.8 | of 2,554 (Radeon Instinct MI300X) |
| Floating-point processing power | 2.634 TFLOPS | of 126 (RTX PRO 6000 Blackwell) |
| ROPs | 32 | of 512 (Moore Threads MTT S4000) |
| TMUs | 112 | of 1280 (Data Center GPU Max NEXT) |
Form factor & compatibility
This section provides details about the physical dimensions of GeForce GTX 670 and its compatibility with other computer components. This information is useful when selecting a computer configuration or upgrading an existing one. For desktop graphics cards, it includes details about the interface and bus (for motherboard compatibility) and additional power connectors (for power supply compatibility).
| Bus support | PCI Express 3.0 | |
| Interface | PCIe 3.0 x16 | |
| Length | 241 mm | |
| Height | 4.376" (11.1 cm) | |
| Width | 2-slot | |
| Supplementary power connectors | 2x 6-pin | |
| SLI options | + |
VRAM capacity and type
Parameters of memory installed on GeForce GTX 670: its type, size, bus, clock and resulting bandwidth. Note that GPUs integrated into processors have no dedicated memory and use a shared part of system RAM instead.
| Memory type | GDDR5 | |
| Maximum RAM amount | 2 GB | of 288 GB (Radeon Instinct MI325X) |
| Memory bus width | 256-bit GDDR5 | of 8192 Bit (Radeon Instinct MI250X) |
| Memory clock speed | 6.0 GB/s | of 16000 GB/s (GeForce RTX 4050 Mobile) |
| Memory bandwidth | 192.2 GB/s | of 5,171 GB/s (Radeon Instinct MI300X) |
Connectivity and outputs
Types and number of video connectors present on GeForce GTX 670. As a rule, this section is relevant only for desktop reference graphics cards, since for notebook ones the availability of certain video outputs depends on the laptop model, while non-reference desktop models can (though not necessarily will) bear a different set of video ports.
| Display Connectors | One Dual Link DVI-I, One Dual Link DVI-D, One HDMI, One DisplayPort | |
| Multi monitor support | 4 displays | |
| HDMI | + | |
| HDCP | + | |
| Maximum VGA resolution | 2048x1536 | |
| Audio input for HDMI | Internal |
Supported technologies
Technological solutions and APIs supported by GeForce GTX 670. You'll probably need this information if you need some particular technology for your purposes.
| 3D Blu-Ray | + | |
| 3D Gaming | + | |
| 3D Vision | + |
API and SDK compatibility
APIs supported by GeForce GTX 670, sometimes including their particular versions.
| DirectX | 12 (11_0) | |
| Shader Model | 5.1 | |
| OpenGL | 4.2 | of 4.6 (GeForce RTX 5090 D) |
| OpenCL | 1.2 | |
| Vulkan | 1.1.126 | |
| CUDA | + |
Benchmark performance
Synthetic benchmark performance of GeForce GTX 670. The combined score is measured on a 0-100 point scale.
Combined synthetic benchmark score
This is our combined benchmark score.
Passmark
This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.
3DMark Fire Strike Graphics
Fire Strike is a DirectX 11 benchmark for gaming PCs. It features two separate tests displaying a fight between a humanoid and a fiery creature made of lava. Using 1920x1080 resolution, Fire Strike shows off some realistic graphics and is quite taxing on hardware.
GeekBench 5 OpenCL
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses OpenCL API by Khronos Group.
GeekBench 5 Vulkan
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses Vulkan API by AMD & Khronos Group.
GeekBench 5 CUDA
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses CUDA API by NVIDIA.
Octane Render OctaneBench
This is a special benchmark measuring graphics card performance in OctaneRender, which is a realistic GPU rendering engine by OTOY Inc., available either as a standalone program, or as a plugin for 3DS Max, Cinema 4D and many other apps. It renders four different static scenes, then compares render times with a reference GPU which is currently GeForce GTX 980. This benchmark has nothing to do with gaming and is aimed at professional 3D graphics artists.
Unigine Heaven 4.0
This is an old DirectX 11 benchmark, a newer version of Unigine 3.0 with relatively small differences. It displays a fantasy medieval town sprawling over several flying islands. The benchmark is still sometimes used, despite its significant age, as it was released back in 2013.
Send your test results of GeForce GTX 670.
AMD equivalent
According to our data, the closest AMD alternative to GeForce GTX 670 is Radeon HD 7970, which is slower by 2% and lower by 4 positions in our ranking.
Here are some closest AMD rivals to GeForce GTX 670:
Similar GPUs
Here is our recommendation of several graphics cards that are more or less close in performance to the one reviewed.
Recommended processors
These processors are most commonly used with GeForce GTX 670 according to our statistics.
