GEFORCE

NVIDIA GeForce FX 5900

NVIDIA graphics card specifications and benchmark scores

128 MB
VRAM
MHz Boost
TDP
256
Bus Width

At a Glance

NVIDIA
VRAM 128 MB
Bus Width 256-bit
Memory Type DDR
Architecture Rankine
nm
Process 130 nm
Released May 2003

NVIDIA GeForce FX 5900 Specifications

GeForce FX 5900 GPU Core

Shader units and compute resources

The NVIDIA GeForce FX 5900 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.

TMUs
8
ROPs
4

FX 5900 Clock Speeds

GPU and memory frequencies

Clock speeds directly impact the GeForce FX 5900'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 FX 5900 by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.

GPU Clock
400 MHz
Memory Clock
425 MHz 850 Mbps effective
GDDR GDDR 6X 6X

NVIDIA's GeForce FX 5900 Memory

VRAM capacity and bandwidth

VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The GeForce FX 5900'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
128 MB
VRAM
128 MB
Memory Type
DDR
VRAM Type
DDR
Memory Bus
256 bit
Bus Width
256-bit
Bandwidth
27.20 GB/s

FX 5900 Theoretical Performance

Compute and fill rates

Theoretical performance metrics provide a baseline for comparing the NVIDIA GeForce FX 5900 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.

Pixel Rate
1.600 GPixel/s
Texture Rate
3.200 GTexel/s

Rankine Architecture & Process

Manufacturing and design details

The NVIDIA GeForce FX 5900 is built on NVIDIA's Rankine 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 FX 5900 will perform in GPU benchmarks compared to previous generations.

Architecture
Rankine
GPU Name
NV35
Process Node
130 nm
Foundry
TSMC
Transistors
135 million
Die Size
207 mm²
Density
652.2K / mm²

NVIDIA's GeForce FX 5900 Power & Thermal

TDP and power requirements

Power specifications for the NVIDIA GeForce FX 5900 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 FX 5900 to maintain boost clocks without throttling.

Power Connectors
1x Molex
Suggested PSU
200 W

GeForce FX 5900 by NVIDIA Physical & Connectivity

Dimensions and outputs

Physical dimensions of the NVIDIA GeForce FX 5900 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
Single-slot
Length
218 mm 8.6 inches
Bus Interface
AGP 8x
Display Outputs
1x DVI1x VGA1x S-Video
Display Outputs
1x DVI1x VGA1x S-Video

NVIDIA API Support

Graphics and compute APIs

API support determines which games and applications can fully utilize the NVIDIA GeForce FX 5900. 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
9.0a
DirectX
9.0a
OpenGL
1.5 (full) 2.0 (partial)
OpenGL
1.5 (full) 2.0 (partial)

GeForce FX 5900 Product Information

Release and pricing details

The NVIDIA GeForce FX 5900 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 FX 5900 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
May 2003
Launch Price
399 USD
Production
End-of-life
Predecessor
GeForce 4 Ti
Successor
GeForce 6 AGP

GeForce FX 5900 Benchmark Scores

No benchmark data available for this GPU.

About NVIDIA GeForce FX 5900

The NVIDIA GeForce FX 5900 targets the high-end segment of its generation, built on the NV35 chip with the Rankine architecture. It arrives with 128 MB of DDR memory, a 256-bit bus, and a launch MSRP of 399 USD, positioning it as a premium AGP 8x solution of its era.

Benchmark Performance

The FACT PACK contains no benchmark scores for the FX 5900, and the `nearestRivals` array is empty, so no direct percentage deltas or comparative performance indices can be cited. The `avgBenchmarkScore` stands at 0, while the `percentileVsAllGpus` is 50, placing it exactly at the midpoint of all GPUs tracked in the database, a neutral standing that suggests neither dominant nor lagging performance in aggregate. Without raw scores, the data indicates that the FX 5900’s real-world performance must be inferred from its architectural attributes rather than measured results. The pixel rate is listed at 1.600 GPixel/s, and the texture rate at 3.200 GTexel/s, which are the only concrete throughput figures available. These rates, combined with 8 TMUs and 4 ROPs, suggest a design tuned for balanced fill-rate workloads rather than extreme shader complexity. The FP32 and FP16 compute values are absent from the pack, meaning no floating-point throughput can be quantified; the card’s compute capability remains unverifiable from this dataset. The DirectX support is 9.0a, and OpenGL is listed as 1.5 (full) with 2.0 (partial), which frames it as an early DirectX 9 part with incomplete OpenGL 2.0 compliance, an important caveat for legacy titles relying on that API. The process node is 130 nm, with 135 million transistors on a 207 mm² die, yielding a transistor density of 652.2K per mm², but this does not translate into a benchmark figure. The production status is end-of-life, and the release date is May 2003, so any performance expectations should be contextualized to that period’s software landscape. The lack of scored benchmarks means the percentile of 50 is the sole statistical anchor, indicating that half of all tracked GPUs score better and half score worse, a median position with no margin information.

Memory Subsystem

The FX 5900 uses 128 MB of DDR memory, which is a modest capacity even for its release window, but the 256-bit bus width is a significant asset. The memory clock runs at 425 MHz, translating to 850 Mbps effective, and the resulting bandwidth is 27.20 GB/s. This bandwidth figure is the key differentiator: a 256-bit bus at 850 Mbps effective yields a throughput that supports high-resolution textures and heavy fill-rate demands. For the early DirectX 9 era, 128 MB was a common high-end capacity, though it could limit texture-heavy scenes at extreme resolutions. The bus width of 256 bit means the memory subsystem can move data in large chunks, which helps sustain the pixel and texture rates listed, 1.600 GPixel/s and 3.200 GTexel/s, respectively. At 1024x768 or 1280x1024, the 27.20 GB/s bandwidth likely suffices for most titles, but the 128 MB frame buffer may become a constraint when enabling 4x anti-aliasing or high anisotropic filtering, as those settings consume both bandwidth and capacity. The memory type is DDR, not GDDR, so the effective data rate of 850 Mbps is the peak per pin; no further overclocking headroom is documented in the pack. The ROP count of 4 means that pixel fill rate is capped at 1.600 GPixel/s, which is a relatively low number for a high-end card of that generation, and this could bottleneck memory bandwidth in scenarios with heavy overdraw. The 27.20 GB/s bandwidth, however, is a strong figure that can compensate for the low ROP count in many workloads, as texture streaming and vertex data transfers benefit from the wide bus. For resolutions above 1600x1200, the 128 MB capacity is likely insufficient for modern (circa 2003) texture sets, but the bandwidth itself is not the limiting factor, the capacity is. In summary, the memory subsystem is a mixed bag: wide and fast for its class, but limited in total storage, which directly impacts high-resolution gaming.

Who Should Consider It

Based on the data, the FX 5900 is suited for users running games at 1024x768 or 1280x1024 with moderate settings, where the 27.20 GB/s bandwidth and 3.200 GTexel/s texture rate can be fully utilized. The pixel rate of 1.600 GPixel/s suggests that 1600x1200 or higher resolutions with anti-aliasing will strain the 4 ROPs, resulting in potential frame rate drops. The 128 MB memory capacity is adequate for 32-bit color at 1280x1024, but enabling 4x full-scene anti-aliasing or high-resolution shadows may exceed the frame buffer, causing texture thrashing. The DirectX 9.0a support means early DX9 titles will run, but the partial OpenGL 2.0 support could cause issues with OpenGL-based games relying on newer features. The card’s AGP 8x interface is a match for motherboards of that era, and the single-slot design with one Molex power connector makes installation straightforward in most cases. The suggested PSU is 200 W, which is low by modern standards but typical for 2003 hardware. Users with a 130 nm process node card should expect significant heat output, though the pack lists no TDP figure, so thermal requirements cannot be quantified. The FX 5900 is not for 4K or ultra-high refresh rates, those are irrelevant to its generation, but for 1280x1024 or 1600x1200 gaming with reduced detail, the data supports its capability. The 50th percentile ranking implies it sits at the median of all GPUs, so it is neither a top-tier performer nor a weak one; it is a balanced choice for mainstream high-end systems of its time. The lack of benchmarks means specific frame rates cannot be stated, but the architectural figures (1.600 GPixel/s, 3.200 GTexel/s) provide a baseline for expected throughput. Enthusiasts who prioritize texture quality over resolution will find the 256-bit bus beneficial, while those demanding high pixel fill will be disappointed by the 4 ROPs.

How It Compares

The `nearestRivals` array is empty, so no direct comparison to specific competing products can be made from the FACT PACK. The `predecessor` is the GeForce 4 Ti, and the `successor` is the GeForce 6 AGP, but no scores or deltas are provided for either. The FX 5900’s percentile of 50 is a global metric, not a head-to-head figure, so its standing relative to any named rival is indeterminate. The absence of rival data means that any claims about beating or losing to a specific card would be unsupported. The architecture is Rankine, which supersedes the older NV25-based GeForce 4 Ti, but no benchmark comparison exists in the pack to quantify the generational leap. The process node improved to 130 nm from the older 150 nm parts, but that is a manufacturing detail, not a performance metric. The memory bandwidth of 27.20 GB/s is a concrete number, but without rival bandwidth figures, it cannot be compared. The pixel rate of 1.600 GPixel/s and texture rate of 3.200 GTexel/s are likewise isolated values. The successor, GeForce 6 AGP, would presumably offer higher scores, but the pack does not state any. Therefore, the FX 5900’s competitive position cannot be established with the given data; it exists as a standalone entry with a median percentile. The launch MSRP of 399 USD is noted, but no rival pricing exists to contextualize it. The production status is end-of-life, indicating it has been superseded, but the extent of that supersession is unquantified. In short, this section must rely solely on the empty rival list, concluding that no relational analysis is possible.

FAQ

Q: What is the memory bandwidth of the FX 5900?

A: The memory bandwidth is 27.20 GB/s, derived from a 256-bit bus and 425 MHz memory clock with 850 Mbps effective data rate.

Q: How many ROPs does the FX 5900 have, and what pixel rate does that support?

A: The card has 4 ROPs, which supports a pixel rate of 1.600 GPixel/s.

Q: What is the transistor count and die size?

A: The NV35 chip contains 135 million transistors on a 207 mm² die, manufactured on a 130 nm process at TSMC.

Q: Does the FX 5900 support DirectX 9?

A: Yes, it supports DirectX 9.0a, but OpenGL support is only 1.5 (full) and 2.0 (partial).

Q: What is the percentile ranking of the FX 5900 among all GPUs?

A: The percentile is 50, meaning it ranks exactly at the median of all GPUs tracked in the database, with no benchmark scores recorded.

Q: What is the launch MSRP of the FX 5900?

A: The launch MSRP is 399 USD, and the card was released in May 2003, with a production status of end-of-life.

Compare GeForce FX 5900 with Other GPUs

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

Browse GPUs