GEFORCE

NVIDIA GeForce GT 640M

NVIDIA graphics card specifications and benchmark scores

2 GB
VRAM
709
MHz Boost
32W
TDP
128
Bus Width

At a Glance

NVIDIA
VRAM 2 GB
Boost Clock 709 MHz
Shaders 384
Bus Width 128-bit
TDP 32W
Memory Type DDR3
Architecture Kepler
nm
Process 28 nm
Released Mar 2012

NVIDIA GeForce GT 640M Specifications

GeForce GT 640M GPU Core

Shader units and compute resources

The NVIDIA GeForce GT 640M 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

GT 640M Clock Speeds

GPU and memory frequencies

Clock speeds directly impact the GeForce GT 640M'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 GT 640M by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.

Base Clock
624 MHz
Base Clock
624 MHz
Boost Clock
709 MHz
Boost Clock
709 MHz
Memory Clock
900 MHz 1800 Mbps effective
GDDR GDDR 6X 6X

NVIDIA's GeForce GT 640M Memory

VRAM capacity and bandwidth

VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The GeForce GT 640M'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
2 GB
VRAM
2,048 MB
Memory Type
DDR3
VRAM Type
DDR3
Memory Bus
128 bit
Bus Width
128-bit
Bandwidth
28.80 GB/s

GeForce GT 640M by NVIDIA Cache

On-chip cache hierarchy

On-chip cache provides ultra-fast data access for the GT 640M, 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

GT 640M Theoretical Performance

Compute and fill rates

Theoretical performance metrics provide a baseline for comparing the NVIDIA GeForce GT 640M 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)
544.5 GFLOPS
FP64 (Double)
22.69 GFLOPS (1:24)
Pixel Rate
5.672 GPixel/s
Texture Rate
22.69 GTexel/s

Kepler Architecture & Process

Manufacturing and design details

The NVIDIA GeForce GT 640M 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 GT 640M 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 GT 640M Power & Thermal

TDP and power requirements

Power specifications for the NVIDIA GeForce GT 640M 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 GT 640M to maintain boost clocks without throttling.

TDP
32 W
TDP
32W
Power Connectors
None

GeForce GT 640M by NVIDIA Physical & Connectivity

Dimensions and outputs

Physical dimensions of the NVIDIA GeForce GT 640M 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
IGP
Bus Interface
PCIe 3.0 x16
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 GT 640M. 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 GT 640M Product Information

Release and pricing details

The NVIDIA GeForce GT 640M 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 GT 640M 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
Mar 2012
Production
End-of-life
Predecessor
GeForce 500M
Successor
GeForce 700M

GeForce GT 640M Benchmark Scores

geekbench_metalSource

Geekbench Metal tests GPU compute using Apple's Metal API. This shows how NVIDIA GeForce GT 640M performs in macOS and iOS applications that leverage GPU acceleration. Metal provides low-overhead access to Apple silicon GPUs.

geekbench_metal #155 of 161
1,478
1%
Max: 226,821

geekbench_openclSource

Geekbench OpenCL tests GPU compute performance using the cross-platform OpenCL API. This shows how NVIDIA GeForce GT 640M handles parallel computing tasks like video encoding and scientific simulations.

geekbench_opencl #549 of 643
3,192
1%
Max: 388,405
Compare with other GPUs

About NVIDIA GeForce GT 640M

The NVIDIA GeForce GT 640M is a Kepler-generation mobile GPU from the GeForce 600M series, built on a 28 nm process at TSMC with 1,270 million transistors on a 118 mm² die. It targets the entry-level laptop segment, and its benchmark data places it firmly in the lower echelon of the GPU landscape, holding a 13th percentile ranking among all GPUs. With an average benchmark score of 2291, the GT 640M is a product of its 2012 era, offering basic acceleration for everyday tasks and older titles, but its performance profile is tightly clustered with a set of similarly positioned rivals.

Benchmark Performance

The GT 640M’s synthetic benchmark results reveal a GPU that is essentially at parity with its immediate competitors, with deltas so small they fall within typical run-to-run variance. Its average score of 2291 is derived from two specific tests: a Geekbench Metal score of 1389 and a Geekbench OpenCL score of 3192. The OpenCL result is notably more than double the Metal score, which is unsurprising given that Metal is an Apple-centric API and this GPU is primarily associated with Windows-based laptops.

Against its nearest rival, the NVIDIA GeForce GT 640M LE, the standard GT 640M trails by a negligible 0.1%. The LE variant scores 2293, making the two effectively identical in practical terms. This near-zero delta suggests that the performance difference between the standard and LE versions is purely academic, likely stemming from minor clock variations that do not translate into measurable real-world gains.

The gap widens only slightly when compared to the NVIDIA Quadro M1000M, which posts an average score of 2326. The GT 640M is 1.5% behind this professional-grade mobile GPU. This is a surprisingly small margin, indicating that for compute workloads, the Quadro’s professional driver optimizations do not provide a significant advantage over the consumer-oriented GT 640M in these specific benchmark tests.

The two remaining rivals, the GeForce GT 550M and GT 630M, score 2363 and 2367 respectively. The GT 640M trails the GT 550M by 3% and the GT 630M by 3.2%. These deltas are still modest, but they do show a consistent trend: the GT 640M sits at the bottom of this five-way comparison. The data indicates that while the GT 640M is not a performance outlier, its Kepler architecture does not provide a generational leap over the older Fermi-based GT 550M in these synthetic tests, as the gap is within 3%.

Ray Tracing and Feature Set

The GT 640M does not include dedicated ray tracing cores or tensor cores, as these features were introduced in later architectures. Its feature set is defined by the Kepler architecture’s capabilities, which are centered on traditional rasterization. The GPU integrates 384 shading units, 32 texture mapping units, and 16 raster output pipelines, providing a baseline for pixel and texture throughput.

In terms of API support, the GT 640M supports DirectX 12 (11_0), which is a partial implementation of the DirectX 12 feature set, effectively capping it at feature level 11_0. This means it can run DirectX 12 titles, but without the advanced features like bindless resources or conservative rasterization that higher feature levels offer. OpenGL 4.6 and Vulkan 1.2.175 are fully supported, providing modern cross-platform API access for a GPU of this vintage.

The pixel rate is 5.672 GPixel/s, and the texture rate is 22.69 GTexel/s, with FP32 compute at 544.5 GFLOPS. These figures are modest, reflecting the GPU’s entry-level positioning. For a user seeking to play modern games, the lack of ray tracing hardware is not a surprise, but the DirectX 12 (11_0) limitation means that some newer titles may not run with full graphical fidelity or may require compatibility modes.

Memory Subsystem

The GT 640M is equipped with 2 GB of DDR3 memory on a 128-bit bus, delivering a memory bandwidth of 28.80 GB/s. The memory clock runs at 900 MHz, with an effective data rate of 1800 Mbps. This configuration is a significant bottleneck for the GPU, as the bandwidth is quite low by modern standards.

At 1080p resolution, the 28.80 GB/s bandwidth will likely constrain performance in texture-heavy scenes or when anti-aliasing is enabled. The 2 GB VRAM capacity is adequate for the era’s games, but modern titles with high-resolution textures will quickly exceed this limit, leading to texture streaming issues or reduced detail settings. The 128-bit bus width is narrow, which further limits the data throughput.

For high-resolution gaming, this memory subsystem is a clear weak point. The combination of DDR3 memory and a narrow bus means that the GPU cannot feed its 384 shading units efficiently, particularly in scenarios where large amounts of data need to be moved quickly. The data suggests that the GT 640M is best suited for 720p or 1366x768 resolutions, where the bandwidth demands are lower and the GPU can perform closer to its theoretical limits.

How It Compares

vs. NVIDIA GeForce GT 640M LE: The standard GT 640M is marginally slower than its LE counterpart, with a 0.1% deficit. This is effectively a tie, and the performance difference is irrelevant in practical use. Both GPUs will deliver identical frame rates in games, and the choice between them would come down to other factors like power efficiency or availability.

vs. NVIDIA Quadro M1000M: The GT 640M is 1.5% behind the Quadro M1000M in average score. This is a notable result because the Quadro is a professional GPU with higher certification standards and typically a higher price point. The data shows that for raw compute in these benchmarks, the GT 640M holds its own, suggesting that the Quadro’s value proposition lies in driver stability and application certifications rather than raw performance.

vs. NVIDIA GeForce GT 550M: The GT 640M trails the older GT 550M by 3%. This is a surprising result, as one might expect the newer Kepler architecture to outperform the older Fermi architecture by a larger margin. The 3% delta implies that the GT 640M’s architectural improvements are offset by its lower clock speeds or memory configuration, resulting in a negligible performance gain over its predecessor.

vs. NVIDIA GeForce GT 630M: The GT 640M is 3.2% behind the GT 630M. Similar to the GT 550M comparison, this shows that the GT 640M is not a clear step up within its own lineup. The data indicates that these four GPUs are all within a 3.2% performance band, meaning that users upgrading from any of these to the GT 640M would see no meaningful improvement in synthetic benchmarks.

Power and Cooling

The GT 640M has a TDP of 32 W, making it a low-power part suitable for thin and light laptops. It does not require any external power connectors, drawing all its power from the motherboard via the PCIe 3.0 x16 interface. The slot width is listed as IGP, indicating it is an integrated GPU on the motherboard package, not a discrete MXM module.

Because of its 32 W TDP, the cooling solution can be modest. A capable air cooler with a small heat sink and fan is sufficient to keep thermals in check. The lack of power connectors simplifies laptop design, as the GPU does not add significant power delivery complexity. There is no suggested PSU rating provided, but for a laptop, this is irrelevant, as the power supply is external and sized for the entire system.

The low power draw is one of the GT 640M’s strengths, enabling longer battery life in laptops compared to higher-TDP discrete GPUs. However, this comes at the cost of performance, as the GPU is limited to the power envelope of a 32 W part.

FAQ

Q: What is the average benchmark score of the NVIDIA GeForce GT 640M?

A: The average benchmark score is 2291, based on Geekbench Metal and OpenCL results of 1389 and 3192, respectively.

Q: Does the GT 640M support DirectX 12 Ultimate?

A: No, it supports DirectX 12 (11_0), which is a partial implementation that does not include the full feature set of DirectX 12 Ultimate.

Q: How much VRAM does the GT 640M have, and what type is it?

A: It has 2 GB of DDR3 memory on a 128-bit bus, providing a bandwidth of 28.80 GB/s.

Q: What is the performance difference between the GT 640M and the GT 640M LE?

A: The GT 640M is 0.1% slower than the GT 640M LE, which scores 2293, making the two GPUs effectively equal in performance.

Q: Does the GT 640M require a power connector?

A: No, it requires no power connectors, as its TDP is 32 W and it draws power from the PCIe slot.

Q: What is the GT 640M’s percentile ranking among all GPUs?

A: It ranks in the 13th percentile, indicating that it performs better than only 13% of all GPUs in the benchmark database.

Who Should Consider It

The GT 640M is a GPU for users who prioritize low power consumption and basic 3D acceleration over gaming performance. Its 13th percentile ranking places it well below the median, meaning it is not suitable for modern games at high settings. The data shows that it is best suited for 720p gaming with low to medium detail settings in titles from its release era (2012) or older.

For users with a laptop containing this GPU, the 2 GB VRAM and 28.80 GB/s bandwidth will handle esports titles like older MOBAs or CS:GO at playable frame rates, but it will struggle with graphically demanding games released after 2015. The 384 shading units are sufficient for pixel shaders of the time, but the memory bandwidth is a limiting factor.

Given its end-of-life production status, the GT 640M is not a purchase recommendation for new systems. However, for someone using an older laptop for light productivity, media playback, or legacy gaming, this GPU provides a functional, low-power solution. Its performance parity with the GT 640M LE, Quadro M1000M, GT 550M, and GT 630M means that users should not expect any significant performance differences when moving between these GPUs. The GT 640M is a clear example of a product designed for a specific era, and its benchmark data confirms that it has little to offer for modern, high-resolution workloads.

The AMD Equivalent of GeForce GT 640M

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 GT 640M Comparisons

See how the GeForce GT 640M stacks up against similar graphics cards from the same generation and competing brands.

Compare GeForce GT 640M with Other GPUs

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

Browse GPUs