NVIDIA GeForce GTX 660 Rev. 2
NVIDIA graphics card specifications and benchmark scores
At a Glance
NVIDIANVIDIA GeForce GTX 660 Rev. 2 Specifications
GeForce GTX 660 Rev. 2 GPU Core
Shader units and compute resources
The NVIDIA GeForce GTX 660 Rev. 2 GPU core specifications define its raw processing power for graphics and compute workloads. Shading units (also called CUDA cores, stream processors, or execution units depending on manufacturer) handle the parallel calculations required for rendering. TMUs (Texture Mapping Units) process texture data, while ROPs (Render Output Units) handle final pixel output. Higher shader counts generally translate to better GPU benchmark performance, especially in demanding games and 3D applications.
GTX 660 Rev. 2 Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the GeForce GTX 660 Rev. 2's performance in GPU benchmarks and real-world gaming. The base clock represents the minimum guaranteed frequency, while the boost clock indicates peak performance under optimal thermal conditions. Memory clock speed affects texture loading and frame buffer operations. The GeForce GTX 660 Rev. 2 by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
NVIDIA's GeForce GTX 660 Rev. 2 Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The GeForce GTX 660 Rev. 2's memory capacity determines how well it handles high-resolution textures and multiple displays. Memory bandwidth, measured in GB/s, affects how quickly data moves between the GPU and VRAM. Higher bandwidth improves performance in memory-intensive scenarios like 4K gaming. The memory bus width and type (GDDR6, GDDR6X, HBM) significantly influence overall GPU benchmark scores.
GeForce GTX 660 Rev. 2 by NVIDIA Cache
On-chip cache hierarchy
On-chip cache provides ultra-fast data access for the GTX 660 Rev. 2, reducing the need to fetch data from slower VRAM. L1 and L2 caches store frequently accessed data close to the compute units. AMD's Infinity Cache (L3) dramatically increases effective bandwidth, improving GPU benchmark performance without requiring wider memory buses. Larger cache sizes help maintain high frame rates in memory-bound scenarios and reduce power consumption by minimizing VRAM accesses.
GTX 660 Rev. 2 Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the NVIDIA GeForce GTX 660 Rev. 2 against other graphics cards. FP32 (single-precision) performance, measured in TFLOPS, indicates compute capability for gaming and general GPU workloads. FP64 (double-precision) matters for scientific computing. Pixel and texture fill rates determine how quickly the GPU can render complex scenes. While real-world GPU benchmark results depend on many factors, these specifications help predict relative performance levels.
Kepler Architecture & Process
Manufacturing and design details
The NVIDIA GeForce GTX 660 Rev. 2 is built on NVIDIA's Kepler architecture, which defines how the GPU processes graphics and compute workloads. The manufacturing process node affects power efficiency, thermal characteristics, and maximum clock speeds. Smaller process nodes pack more transistors into the same die area, enabling higher performance per watt. Understanding the architecture helps predict how the GTX 660 Rev. 2 will perform in GPU benchmarks compared to previous generations.
NVIDIA's GeForce GTX 660 Rev. 2 Power & Thermal
TDP and power requirements
Power specifications for the NVIDIA GeForce GTX 660 Rev. 2 determine PSU requirements and thermal management needs. TDP (Thermal Design Power) indicates the heat output under typical loads, guiding cooler selection. Power connector requirements ensure adequate power delivery for stable operation during demanding GPU benchmarks. The suggested PSU wattage accounts for the entire system, not just the graphics card. Efficient power delivery enables the GeForce GTX 660 Rev. 2 to maintain boost clocks without throttling.
GeForce GTX 660 Rev. 2 by NVIDIA Physical & Connectivity
Dimensions and outputs
Physical dimensions of the NVIDIA GeForce GTX 660 Rev. 2 are critical for case compatibility. Card length, height, and slot width determine whether it fits in your chassis. The PCIe interface version affects bandwidth for communication with the CPU. Display outputs define monitor connectivity options, with modern cards supporting multiple high-resolution displays simultaneously. Verify these specifications against your case and motherboard before purchasing to ensure a proper fit.
NVIDIA API Support
Graphics and compute APIs
API support determines which games and applications can fully utilize the NVIDIA GeForce GTX 660 Rev. 2. DirectX 12 Ultimate enables advanced features like ray tracing and variable rate shading. Vulkan provides cross-platform graphics capabilities with low-level hardware access. OpenGL remains important for professional applications and older games. CUDA (NVIDIA) and OpenCL enable GPU compute for video editing, 3D rendering, and scientific applications. Higher API versions unlock newer graphical features in GPU benchmarks and games.
GeForce GTX 660 Rev. 2 Product Information
Release and pricing details
The NVIDIA GeForce GTX 660 Rev. 2 is manufactured by NVIDIA as part of their graphics card lineup. Release date and launch pricing provide context for comparing GPU benchmark results with competing products from the same era. Understanding the product lifecycle helps evaluate whether the GeForce GTX 660 Rev. 2 by NVIDIA represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.
GeForce GTX 660 Rev. 2 Benchmark Scores
No benchmark data available for this GPU.
About NVIDIA GeForce GTX 660 Rev. 2
The NVIDIA GeForce GTX 660 Rev. 2 comes from the GeForce 600 generation, built by NVIDIA around the GK104 chip using the Kepler architecture. It is manufactured by TSMC on a 28 nm process, with 3,540 million transistors packed into a 294 mm² die for a transistor density of 12.0M per mm². Released on 2014-09-12, the product is listed as end-of-life, with GeForce 500 as its predecessor and GeForce 700 as its successor. The database record for this card has no benchmark scores and no nearest-rival entries; its percentileVsAllGpus value is 50, and its average benchmark score is 0.
Benchmark Performance
The benchmark data for the GTX 660 Rev. 2 is unusually sparse. There are no entries in the benchmarks array, and the nearestRivals array is empty, meaning exact percentage deltas against named competitors cannot be calculated from this record. The only distributional metric available is the percentileVsAllGpus value of 50. That places the card at the median of all GPUs in the database, with as many entries above it as below it. Without measured scores, this median position cannot be expanded into a precise performance ranking, but it anchors the card in the middle of the GPU population rather than in a leading or trailing tier.
Raw throughput figures do provide structural context. The card carries 960 shading units, 80 texture units, and 24 ROPs. Its base clock is 980 MHz, rising to a boost clock of 1032 MHz. From those resources, the record lists 1.981 TFLOPS of FP32 compute, an 82.56 GTexel/s texture rate, and a 20.64 GPixel/s pixel rate. These are the quantitative limits that define what the card can do per second. The absence of an FP16 figure means half-precision throughput is not specified, and the absence of benchmark scores means there is no measured application-level confirmation of how those throughput limits translate into frame rates. The data shows a card with a defined compute envelope, positioned at the median of the database distribution, but without the comparative scores needed for rival-by-rival analysis.
Memory Subsystem
The memory configuration is 2 GB of GDDR5 on a 192-bit bus. The memory clock is 1502 MHz, described as 6 Gbps effective, and the combined interface and clock produce a bandwidth of 144.2 GB/s. For high-resolution rendering, the two most relevant constraints are the frame buffer capacity and the bandwidth available to fill it. The 2 GB capacity sets an absolute limit on how much image data and texture data can reside on the card at once. The 192-bit bus width determines how many bits can move per memory access, and the 6 Gbps effective memory rate is what pushes the final bandwidth to 144.2 GB/s.
Pixel rate and texture rate interact with this memory subsystem. The 20.64 GPixel/s pixel rate reflects how quickly the 24 ROPs can write pixels, which becomes increasingly important as resolution grows. The 82.56 GTexel/s texture rate defines how quickly textures can be sampled, and those samples must travel across the same 144.2 GB/s bus. No memory benchmark results are present in the record, so the exact resolution at which the 2 GB capacity or the 192-bit bandwidth becomes a bottleneck cannot be quantified from these data. What the data makes clear is that high-resolution workloads will be shaped by the capacity and bandwidth limits of this memory interface.
Ray Tracing and Feature Set
The RT cores and tensor cores fields in this record are null, indicating that no ray-tracing hardware or tensor-core acceleration is specified for this card. That matters for workloads that depend on dedicated ray-tracing or tensor-accelerated operations: those specialized paths are not part of the feature set. The card does support DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The DirectX 12 entry is notable because the feature level is listed as 11_0, which defines a specific subset of DirectX 12 functionality rather than the full feature set.
The bus interface is PCIe 3.0 x16, connecting the card to the rest of the system. Display outputs include 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. These outputs define the display connectivity options. The API list gives a baseline for software compatibility: DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175 are all present in the record. The lack of RT and tensor cores is the defining feature-set limitation, while the API list shows a relatively modern software interface layer for a card from this generation.
FAQ
Q: What architecture and chip does the GTX 660 Rev. 2 use?
A: It uses the Kepler architecture with the GK104 chip, manufactured by TSMC on a 28 nm process.
Q: How much memory does it have, and what kind?
A: It has 2 GB of GDDR5 memory on a 192-bit bus, with a memory clock of 1502 MHz and 144.2 GB/s of bandwidth.
Q: What are the core counts and clocks?
A: The card has 960 shading units, 80 texture units, and 24 ROPs. The base clock is 980 MHz and the boost clock is 1032 MHz.
Q: What power supply is recommended?
A: The card has a 140 W TDP, and the suggested PSU is 300 W. Power is delivered through one 6-pin connector.
Q: Does this card support ray tracing?
A: No RT cores or tensor cores are listed in the data. API support includes DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175.
Q: What display outputs are available?
A: The card provides 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2.
How It Compares
The nearestRivals array in this record is empty, so there are no named rival cards to compare against. That means the usual rival-by-rival percentages cannot be produced from the supplied data. Instead, the only comparison anchor is the percentileVsAllGpus value of 50, which places the card exactly at the median of the GPU distribution in the database. The average benchmark score is 0, and the benchmarks array is empty, so no measured score underlies that median position. The product context is available through its predecessor GeForce 500 and successor GeForce 700, but this record contains no scores for those families. Given the empty rival list, any direct comparison to specific cards would require additional data that is not present in this pack.
Power and Cooling
The GTX 660 Rev. 2 is rated at a 140 W TDP. The suggested power supply is 300 W, and the card requires one 6-pin power connector. These figures define the power delivery expectations for installation. The card is dual-slot wide and measures 241 mm in length, or 9.5 inches. That length and slot width are the physical constraints for chassis and slot clearance. The data does not include any cooler details beyond the dual-slot form factor, so fan size, heatsink design, and noise characteristics are not part of this analysis. What the record shows is a moderate power draw with a clear PSU recommendation and a single connector requirement.
Who Should Consider It
This card sits at the 50th percentile of all GPUs in the database, which is a median position. Any user considering it should interpret that as a middle-of-the-pack standing, not a top performer and not a low-end outlier. The memory configuration of 2 GB GDDR5, a 192-bit bus, and 144.2 GB/s bandwidth sets clear expectations for workloads that require large frame buffers or high bandwidth. High-resolution scenarios will be constrained by those memory parameters. The compute rates, including 1.981 TFLOPS FP32, 82.56 GTexel/s texture rate, and 20.64 GPixel/s pixel rate, define the card’s raw processing ceiling.
The API support means DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175 are available, though the DirectX 12 feature level 11_0 limits some of the newer DirectX 12 features. The power and physical requirements are modest: 140 W TDP, a 300 W suggested PSU, one 6-pin connector, a dual-slot width, and a 241 mm length. Because the record contains no measured benchmark scores, any claim about specific resolutions or settings would go beyond the data. What the data does support is a qualification: the GTX 660 Rev. 2 is a median-position card whose memory capacity and bandwidth should be the primary factors in deciding whether it fits a given workload.
The AMD Equivalent of GeForce GTX 660 Rev. 2
Looking for a similar graphics card from AMD? The AMD Radeon RX 480 offers comparable performance and features in the AMD lineup.
Popular NVIDIA GeForce GTX 660 Rev. 2 Comparisons
See how the GeForce GTX 660 Rev. 2 stacks up against similar graphics cards from the same generation and competing brands.
Compare GeForce GTX 660 Rev. 2 with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs