GEFORCE

NVIDIA GeForce GTX 660M Mac Edition

NVIDIA graphics card specifications and benchmark scores

512 MB
VRAM
950
MHz Boost
50W
TDP
128
Bus Width

At a Glance

NVIDIA
VRAM 512 MB
Boost Clock 950 MHz
Shaders 384
Bus Width 128-bit
TDP 50W
Memory Type GDDR5
Architecture Kepler
nm
Process 28 nm
Released Apr 2013

NVIDIA GeForce GTX 660M Mac Edition Specifications

GeForce GTX 660M Mac Edition GPU Core

Shader units and compute resources

The NVIDIA GeForce GTX 660M Mac Edition 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.

Shading Units
384
Shaders
384
TMUs
32
ROPs
16

GTX 660M Mac Edition Clock Speeds

GPU and memory frequencies

Clock speeds directly impact the GeForce GTX 660M Mac Edition'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 660M Mac Edition by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.

Base Clock
950 MHz
Base Clock
950 MHz
Boost Clock
950 MHz
Boost Clock
950 MHz
Memory Clock
1250 MHz 5 Gbps effective
GDDR GDDR 6X 6X

NVIDIA's GeForce GTX 660M Mac Edition Memory

VRAM capacity and bandwidth

VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The GeForce GTX 660M Mac Edition'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.

Memory Size
512 MB
VRAM
512 MB
Memory Type
GDDR5
VRAM Type
GDDR5
Memory Bus
128 bit
Bus Width
128-bit
Bandwidth
80.00 GB/s

GeForce GTX 660M Mac Edition by NVIDIA Cache

On-chip cache hierarchy

On-chip cache provides ultra-fast data access for the GTX 660M Mac Edition, 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.

L1 Cache
16 KB (per SMX)
L2 Cache
256 KB

GTX 660M Mac Edition Theoretical Performance

Compute and fill rates

Theoretical performance metrics provide a baseline for comparing the NVIDIA GeForce GTX 660M Mac Edition 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.

FP32 (Float)
729.6 GFLOPS
FP64 (Double)
30.40 GFLOPS (1:24)
Pixel Rate
7.600 GPixel/s
Texture Rate
30.40 GTexel/s

Kepler Architecture & Process

Manufacturing and design details

The NVIDIA GeForce GTX 660M Mac Edition 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 660M Mac Edition will perform in GPU benchmarks compared to previous generations.

Architecture
Kepler
GPU Name
GK107
Process Node
28 nm
Foundry
TSMC
Transistors
1,270 million
Die Size
118 mm²
Density
10.8M / mm²

NVIDIA's GeForce GTX 660M Mac Edition Power & Thermal

TDP and power requirements

Power specifications for the NVIDIA GeForce GTX 660M Mac Edition 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 660M Mac Edition to maintain boost clocks without throttling.

TDP
50 W
TDP
50W
Power Connectors
None

GeForce GTX 660M Mac Edition by NVIDIA Physical & Connectivity

Dimensions and outputs

Physical dimensions of the NVIDIA GeForce GTX 660M Mac Edition 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.

Slot Width
MXM Module
Bus Interface
MXM-B (3.0)
Display Outputs
Portable Device Dependent
Display Outputs
Portable Device Dependent

NVIDIA API Support

Graphics and compute APIs

API support determines which games and applications can fully utilize the NVIDIA GeForce GTX 660M Mac Edition. 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.

DirectX
12 (11_0)
DirectX
12 (11_0)
OpenGL
4.6
OpenGL
4.6
Vulkan
1.2.175
Vulkan
1.2.175
OpenCL
3.0
CUDA
3.0
Shader Model
6.5 (5.1)

GeForce GTX 660M Mac Edition Product Information

Release and pricing details

The NVIDIA GeForce GTX 660M Mac Edition 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 660M Mac Edition by NVIDIA represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.

Manufacturer
NVIDIA
Release Date
Apr 2013
Production
End-of-life
Predecessor
GeForce 500M
Successor
GeForce 700M

GeForce GTX 660M Mac Edition Benchmark Scores

No benchmark data available for this GPU.

About NVIDIA GeForce GTX 660M Mac Edition

The NVIDIA GeForce GTX 660M Mac Edition is a 28 nm Kepler-generation mobile GPU built by TSMC, with the GK107 chip at its core. It packs 1,270 million transistors onto a 118 mm² die, giving a transistor density of 10.8M / mm², and belongs to the GeForce 600M family. The product is marked as end-of-life in the fact pack and was released on March 31, 2013, with the GeForce 500M as its predecessor and GeForce 700M as its successor.

Benchmark Performance

The fact pack records no per-game benchmark scores for the GTX 660M Mac Edition; the benchmarks array is empty. That means the database has no FPS or synthetic test entries to compare directly against rival cards. The only relative metric supplied is percentileVsAllGpus, which sits at 50, placing this GPU at the midpoint of the database. The average benchmark score is 0, which in this case reflects the absence of populated benchmark records rather than a measured performance outcome. Because the nearestRivals list is empty, no deltaPct values can be reported.

The compute specification provides the clearest performance indicators. The GPU clock is fixed at 950 MHz for both base and boost, with no dynamic boost range listed. It contains 384 shading units, 32 texture mapping units, and 16 ROPs. Those resources produce 729.6 GFLOPS of FP32 throughput, 30.40 GTexel/s of texture fill rate, and 7.600 GPixel/s of pixel fill rate. The memory side runs at 1250 MHz, or 5 Gbps effective, across a 128-bit bus for 80.00 GB/s of bandwidth.

Those numbers describe a compact Kepler part aimed at mobile platforms. The FP32 figure of 729.6 GFLOPS is the headline compute measure, while the texture and pixel rates show how quickly the shading units can feed the 16 ROPs. Without rival scores, the data does not support a percentage comparison, but the 50th percentile position indicates a database-wide middle ranking. Any claim about precise deltas relative to other GPUs cannot be derived from this fact pack.

Who Should Consider It

This is an MXM Module GPU with display outputs described as portable-device dependent. That makes it a candidate for laptop or compact mobile systems using the MXM-B (3.0) interface, not a standalone desktop card. The 512 MB frame buffer is the dominant constraint for any user considering this part. At higher resolutions and with texture-heavy settings, a 512 MB GDDR5 buffer will be filled quickly. The 80.00 GB/s bandwidth and 128-bit bus are modest, so the memory subsystem will become the limiting factor before the 729.6 GFLOPS compute rate is fully exercised.

The target user is someone running lighter rendering loads or older games where the small VRAM pool is not a problem. Lower resolution and reduced texture detail will keep memory pressure manageable. The fixed 950 MHz clock and 384 shading units are enough for straightforward 3D work, but the data does not support recommendations for demanding high-resolution settings. Users who need large texture caches or high-resolution frame buffers should look elsewhere, because 512 MB is very small by current standards. For portable systems that can accommodate an MXM module and whose display outputs match the host laptop, this GPU can be a sensible option only within those modest settings.

Ray Tracing and Feature Set

The GTX 660M Mac Edition is based on the Kepler architecture and uses the GK107 chip. The fact pack lists no ray tracing cores and no tensor cores, so hardware ray tracing and tensor-accelerated features are not part of the package. This is a conventional raster-oriented GPU from the GeForce 600M generation.

API support in the fact pack includes DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. The DirectX 12 entry is specifically noted as feature level 11_0, which means it carries the DirectX 12 API label but with the feature set of an 11_0-class device. OpenGL 4.6 and Vulkan 1.2.175 give it modern API access for compatible software. The absence of RT and tensor cores means any ray tracing or AI workloads would need to fall back to general-purpose shader execution, but the fact pack does not provide performance data for that scenario.

FAQ

Q: What architecture does the GTX 660M Mac Edition use?

A: It uses the Kepler architecture with the GK107 chip, built by TSMC on a 28 nm process. It has 1,270 million transistors on a 118 mm² die with a density of 10.8M / mm².

Q: How much memory does it have?

A: It has 512 MB of GDDR5 memory on a 128-bit bus, running at 1250 MHz with 5 Gbps effective data rate and 80.00 GB/s bandwidth.

Q: Does it support hardware ray tracing?

A: No. The fact pack lists no ray tracing cores and no tensor cores for this GPU.

Q: What power connectors does it require?

A: The fact pack lists no power connectors. The GPU has a 50 W TDP, and no suggested PSU is recorded.

Q: What display outputs does it have?

A: Display outputs are listed as portable-device dependent, meaning they rely on the host portable system rather than being fixed outputs on the module.

Q: Is this GPU still in production?

A: No. The production status is end-of-life, and the release date is March 31, 2013, with the GeForce 500M as its predecessor and GeForce 700M as its successor.

Memory Subsystem

The memory subsystem consists of 512 MB of GDDR5 on a 128-bit bus, with a memory clock of 1250 MHz and an effective data rate of 5 Gbps. Total bandwidth is 80.00 GB/s. The combination of a small capacity and a narrow bus means this is not a memory-heavy part. For a 512 MB frame buffer, 80.00 GB/s is the available bandwidth envelope, and it will be the practical ceiling for transferring textures, geometry, and frame data at the same time.

At higher resolutions, the capacity limit of 512 MB becomes the more pressing issue. Even if the compute unit can generate pixels at 7.600 GPixel/s, the frame buffer must hold the color buffer, depth data, and textures. The 128-bit bus width is a further constraint because it ties the memory controller to a lower peak data path than wider-bus designs. In practice, users will need to keep resolution and texture quality low enough that the 512 MB pool is not exceeded. The 5 Gbps effective memory speed is standard for GDDR5, but the modest capacity and bus width ultimately limit high-resolution usability.

Power and Cooling

The GTX 660M Mac Edition is rated at 50 W TDP. This is a low-power part by design, consistent with mobile use. The module is listed as an MXM Module with an MXM-B (3.0) interface, and no power connectors are required. The fact pack also records no suggested PSU, so there is no power-supply recommendation to report.

Because there are no auxiliary power connectors, power delivery comes through the MXM connector itself. The slot width is described as MXM Module, which is a module form factor rather than a PCIe card width. Cooling is therefore dependent on the host portable device’s thermal solution. The fact pack does not list any cooler, fan, or heatsink details. The 50 W TDP gives system integrators a clear thermal budget, but actual cooling performance will vary by laptop design.

How It Compares

The fact pack contains no nearestRivals entries for the GTX 660M Mac Edition. There are no rival names, no rival scores, and no deltaPct figures to compare against. As a result, this section cannot report percentage deltas relative to competing GPUs. The only comparative data point available is the overall percentileVsAllGpus value of 50, which places the card at the middle of the database’s GPU rankings.

No nearest rival is listed, so there is no single competitor to benchmark against. The absence of rival data limits the analysis to absolute specifications and the database-level percentile. In that context, the GPU is best understood as a mid-ranked mobile part with 729.6 GFLOPS FP32 compute, 7.600 GPixel/s pixel fill, 30.40 GTexel/s texture fill, 512 MB GDDR5, 80.00 GB/s bandwidth, and a 50 W TDP. Those numbers define its position more concretely than any rival comparison, because no direct comparison data is present in the fact pack.

The AMD Equivalent of GeForce GTX 660M Mac Edition

Looking for a similar graphics card from AMD? The AMD Radeon RX 480 offers comparable performance and features in the AMD lineup.

AMD Radeon RX 480

AMD • 8 GB VRAM

View Specs Compare

Popular NVIDIA GeForce GTX 660M Mac Edition Comparisons

See how the GeForce GTX 660M Mac Edition stacks up against similar graphics cards from the same generation and competing brands.

Compare GeForce GTX 660M Mac Edition with Other GPUs

Select another GPU to compare specifications and benchmarks side-by-side.

Browse GPUs