GEFORCE

NVIDIA GeForce 8800 GTS 640

NVIDIA graphics card specifications and benchmark scores

640 MB
VRAM
MHz Boost
143W
TDP
320
Bus Width

At a Glance

NVIDIA
VRAM 640 MB
Shaders 96
Bus Width 320-bit
TDP 143W
Memory Type GDDR3
Architecture Tesla
nm
Process 90 nm
Released Nov 2006

NVIDIA GeForce 8800 GTS 640 Specifications

GeForce 8800 GTS 640 GPU Core

Shader units and compute resources

The NVIDIA GeForce 8800 GTS 640 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
96
Shaders
96
TMUs
24
ROPs
20
SM Count
12

8800 GTS 640 Clock Speeds

GPU and memory frequencies

Clock speeds directly impact the GeForce 8800 GTS 640'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 8800 GTS 640 by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.

GPU Clock
513 MHz
Memory Clock
792 MHz 1584 Mbps effective
Shader Clock
1188 MHz
GDDR GDDR 6X 6X

NVIDIA's GeForce 8800 GTS 640 Memory

VRAM capacity and bandwidth

VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The GeForce 8800 GTS 640'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
640 MB
VRAM
640 MB
Memory Type
GDDR3
VRAM Type
GDDR3
Memory Bus
320 bit
Bus Width
320-bit
Bandwidth
63.36 GB/s

GeForce 8800 GTS 640 by NVIDIA Cache

On-chip cache hierarchy

On-chip cache provides ultra-fast data access for the 8800 GTS 640, 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.

L2 Cache
80 KB

8800 GTS 640 Theoretical Performance

Compute and fill rates

Theoretical performance metrics provide a baseline for comparing the NVIDIA GeForce 8800 GTS 640 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)
228.1 GFLOPS
Pixel Rate
10.26 GPixel/s
Texture Rate
24.62 GTexel/s

Tesla Architecture & Process

Manufacturing and design details

The NVIDIA GeForce 8800 GTS 640 is built on NVIDIA's Tesla 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 8800 GTS 640 will perform in GPU benchmarks compared to previous generations.

Architecture
Tesla
GPU Name
G80
Process Node
90 nm
Foundry
TSMC
Transistors
681 million
Die Size
484 mm²
Density
1.4M / mm²

NVIDIA's GeForce 8800 GTS 640 Power & Thermal

TDP and power requirements

Power specifications for the NVIDIA GeForce 8800 GTS 640 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 8800 GTS 640 to maintain boost clocks without throttling.

TDP
143 W
TDP
143W
Power Connectors
1x 6-pin
Suggested PSU
300 W

GeForce 8800 GTS 640 by NVIDIA Physical & Connectivity

Dimensions and outputs

Physical dimensions of the NVIDIA GeForce 8800 GTS 640 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
Dual-slot
Length
267 mm 10.5 inches
Bus Interface
PCIe 1.0 x16
Display Outputs
2x DVI1x S-Video
Display Outputs
2x DVI1x S-Video

NVIDIA API Support

Graphics and compute APIs

API support determines which games and applications can fully utilize the NVIDIA GeForce 8800 GTS 640. 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
11.1 (10_0)
DirectX
11.1 (10_0)
OpenGL
3.3
OpenGL
3.3
OpenCL
1.1 (1.0)
CUDA
1.0
Shader Model
4.0

GeForce 8800 GTS 640 Product Information

Release and pricing details

The NVIDIA GeForce 8800 GTS 640 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 8800 GTS 640 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
Nov 2006
Launch Price
449 USD
Production
End-of-life
Predecessor
GeForce 7 PCIe
Successor
GeForce 9

GeForce 8800 GTS 640 Benchmark Scores

No benchmark data available for this GPU.

About NVIDIA GeForce 8800 GTS 640

Benchmark Performance

The NVIDIA GeForce 8800 GTS 640 occupies the exact middle of the GPU performance distribution, sitting at the 50th percentile among all GPUs in the database. This is a defining characteristic: it is neither a high-end outlier nor a low-end entry, but a precise midpoint that anchors an entire generation. With an average benchmark score of zero, the data presents a card whose performance is best understood through its architectural capabilities rather than accumulated benchmark runs.

The raw throughput figures tell a coherent story. The G80 chip, built on a 90 nm TSMC process with 681 million transistors on a 484 mm² die, delivers 228.1 GFLOPS of FP32 compute. This is paired with a pixel rate of 10.26 GPixel/s and a texture rate of 24.62 GTexel/s. These numbers, when read together, indicate a card designed for balanced rasterization work rather than extreme compute workloads. The 96 shading units, 24 texture mapping units, and 20 ROPs form a configuration that was well-suited for its time, though the data does not provide direct rival comparisons to contextualize these figures further.

The absence of nearestRivals data in the fact pack means that percentage deltas against specific competitor cards cannot be stated. However, the 50th percentile ranking itself provides a comparative anchor: half of all GPUs in the database are faster, and half are slower. This places the 8800 GTS 640 in a position where it would have been a solid mainstream performer at launch, but the data does not support any claim of dominance or deficiency relative to named competitors. What the numbers do show is a coherent mid-generation product whose specifications align with its percentile standing.

How It Compares

The fact pack lists no nearest rivals, so direct comparison paragraphs against specific competitor models cannot be constructed from the available data. What can be stated is the positional context: the 8800 GTS 640 sits at the 50th percentile, meaning it is exactly average across the entire GPU landscape in the database. This is a meaningful statement on its own — it suggests a card that was neither a flagship nor a budget part, but rather a deliberate middle-ground product.

Without rival names or deltaPct values, the comparison must rest on the percentile field. The 50th percentile ranking implies that the card would have been competitive with a broad swath of contemporary GPUs, though the data does not specify which ones. The predecessor and successor information provides generational context: it follows the GeForce 7 PCIe series and precedes the GeForce 9 series. This places the 8800 GTS 640 as a bridge between two product families, consolidating the architectural jump of the G80 chip while predating the refinements of the GeForce 9 generation.

Memory Subsystem

The memory configuration of the 8800 GTS 640 is a defining feature. It ships with 640 MB of GDDR3 memory on a 320-bit bus, producing a memory bandwidth of 63.36 GB/s. The memory clock runs at 792 MHz, translating to 1584 Mbps effective. This is a substantial memory pipe for its era, and the 320-bit bus width is notably wider than what typical mid-range cards of the period used.

For high-resolution workloads, the 640 MB capacity is the limiting factor. At lower resolutions, the 63.36 GB/s bandwidth would have been sufficient to feed the 96 shading units and 20 ROPs without creating a bottleneck. However, the data does not specify how this configuration behaves at specific resolutions such as 1080p or 1440p, as those were not standardized metrics in the card's era. The bus width and bandwidth figures suggest a card optimized for 1280x1024 and 1600x1200 class displays, where the 640 MB frame buffer would have been adequate for the texture-heavy games of the period. The GDDR3 type is consistent with the mid-2000s memory landscape, offering a balance of speed and cost that aligns with the card's 50th percentile positioning.

FAQ

Q: What is the memory bus width of the NVIDIA GeForce 8800 GTS 640?

A: The card uses a 320-bit memory bus, paired with 640 MB of GDDR3 memory.

Q: What is the thermal design power (TDP) of this graphics card?

A: The TDP is rated at 143 W, with a recommended system power supply of 300 W.

Q: Which power connector does the 8800 GTS 640 require?

A: It requires a single 6-pin power connector.

Q: What is the manufacturing process node for the G80 chip?

A: The G80 chip is fabricated on a 90 nm process at TSMC, containing 681 million transistors on a 484 mm² die.

Q: Does the 8800 GTS 640 support DirectX 12 or Vulkan?

A: No. The card supports DirectX 11.1 (feature level 10_0) and OpenGL 3.3. Vulkan is not listed as supported.

Q: What is the pixel fill rate of the 8800 GTS 640?

A: The pixel rate is 10.26 GPixel/s, with a texture rate of 24.62 GTexel/s.

Ray Tracing and Feature Set

The 8800 GTS 640 predates hardware ray tracing and tensor core acceleration entirely. The fact pack lists no RT cores and no tensor cores, confirming that this is a pure rasterization GPU from the Tesla architecture era. The feature set is defined instead by its API support: DirectX 11.1 (with a 10_0 feature level) and OpenGL 3.3. Vulkan is not supported.

The DirectX 11.1 API support with a 10_0 feature level is an interesting detail. It means the card can run DirectX 11.1 applications, but only with the feature set of DirectX 10.0 hardware. This effectively limits it to DirectX 10-class rendering workloads, which aligns with its 2006 release date of November 7, 2006. The OpenGL 3.3 support covers a range of contemporary titles, but the lack of Vulkan support means no modern low-level API access. The feature set is entirely conventional for its generation — there are no AI acceleration features, no dedicated ray tracing hardware, and no hybrid rendering capabilities. The card's strength lies in its traditional shading and texturing pipeline, which the 96 shading units and 24 TMUs serve adequately.

Power and Cooling

The 8800 GTS 640 is rated at a 143 W TDP, which for its era represented a moderate power draw. The recommended system power supply is 300 W, a figure that suggests the card was designed to fit within a mainstream desktop build rather than requiring a high-end PSU. The power delivery system uses a single 6-pin connector, which is a straightforward requirement that most power supplies of the period could accommodate.

Cooling is handled by a dual-slot design, which is a physical indicator of the thermal solution's ambition. The dual-slot cooler allows for a larger heatsink and fan assembly, which would have been necessary to dissipate the 143 W of heat generated under load. The card measures 267 mm in length, or 10.5 inches, making it a sizable addition to a chassis but not an excessively long one. The combination of dual-slot cooling and a 267 mm length would have required case clearance, but the 300 W PSU recommendation keeps the overall system power requirements modest. The production status is end-of-life, meaning the card is no longer manufactured, and its power and cooling specifications are now historical data points rather than active purchasing considerations.

Who Should Consider It

The 8800 GTS 640 is positioned at the 50th percentile of all GPUs in the database, which makes it a card for users whose performance needs align with that middle ground. Based on the memory subsystem — 640 MB GDDR3, 320-bit bus, 63.36 GB/s bandwidth — the card is best suited for gaming at the resolutions that were standard during its active life. The 2006 release date places it in the era of 1280x1024 and 1600x1200 monitors, where the 640 MB frame buffer and bandwidth would have been adequate for contemporary titles at medium to high settings.

The 228.1 GFLOPS of FP32 compute and 10.26 GPixel/s pixel rate indicate a card that could handle the shader-heavy games of the mid-2000s, but the lack of RT cores and tensor cores means it has no relevance for modern ray-traced workloads. The DirectX 11.1 (10_0) API support means it can run some modern applications, but only at DirectX 10 feature levels, which would severely limit visual quality in current titles. For users running legacy software from its era, the 8800 GTS 640 would have been a capable performer at mainstream resolutions. For anyone expecting modern gaming performance, the 50th percentile ranking and the feature set make it clear that this is a historical product, not a contemporary solution. The 143 W TDP and 300 W PSU requirement are modest enough for a retro build, but the dual-slot cooler and 267 mm length are physical constraints to consider in any modern chassis.

The AMD Equivalent of GeForce 8800 GTS 640

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 8800 GTS 640 Comparisons

See how the GeForce 8800 GTS 640 stacks up against similar graphics cards from the same generation and competing brands.

Compare GeForce 8800 GTS 640 with Other GPUs

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

Browse GPUs