NVIDIA Quadro FX 350M

The NVIDIA Quadro FX 350M is a mobile workstation graphics solution built on the Curie architecture, utilizing the G72 chip manufactured by TSMC on a 90 nm process. With a production status of end-of-life and a release date in early 2006, this part occupies a specific historical niche in the Quadro FX Mobile (x500M) generation, positioned between the Quadro FX Go predecessor and the Quadro Fermi-M successor. The data indicates a modest specification set aimed at professional portable workloads of its era.

Power and Cooling

The Quadro FX 350M carries a thermal design power (TDP) of 15 W, a figure that places it firmly in the low-power segment for mobile workstation graphics of its generation. This modest power envelope reflects the chip's compact nature, with a die size of 81 mm² housing 112 million transistors, yielding a transistor density of 1.4M per mm². The low TDP suggests that thermal management is relatively straightforward, allowing for thinner and lighter laptop designs without the need for elaborate cooling solutions.

Power delivery is simplified by the absence of additional power connectors, listed as "None." This indicates the card draws its operational power entirely through the PCIe 1.0 x16 bus interface. Consequently, no specific PSU recommendation is provided in the data, as the power requirements are met by the host system's standard mobile power architecture. The 15 W TDP is a critical constraint for system integrators, as it dictates battery life expectations and chassis thermal design, but the data does not provide a suggested PSU wattage, leaving that to the portable device's overall design.

The memory operates at 450 MHz, with an effective data rate of 900 Mbps. This clock speed, combined with a 128-bit bus width, produces a memory bandwidth of 14.40 GB/s. The combination of a 15 W TDP and this bandwidth profile suggests the card is engineered for balanced performance within a strict power budget, prioritizing sustained professional application output over raw throughput.

Ray Tracing and Feature Set

The Quadro FX 350M is a product of the Curie architecture, which predates the introduction of dedicated ray tracing and tensor core hardware. The data explicitly lists null values for RT cores and tensor cores, confirming the absence of hardware acceleration for ray-traced workloads and AI-driven tensor operations. This positions the card as a pure rasterization engine, reliant on traditional shading pipelines.

The feature set is defined by its API support, which is limited to DirectX 9.0c (9_3) and OpenGL 2.1. There is no Vulkan support listed, reflecting the era of the card's release. For professional applications of the mid-2000s, OpenGL 2.1 support was a key enabler for CAD and DCC software, while DirectX 9.0c provided compatibility with contemporary visualization tools. The data does not include shading unit counts, but the texture mapping units (TMUs) number 4 and render output units (ROPs) number 2, which define the pixel and texture processing capacity.

The pixel rate is specified at 900.0 MPixel/s, and the texture rate is 1.800 GTexel/s. These figures represent the card's fundamental fill-rate capabilities, which are modest by modern standards but were appropriate for its target market. The display outputs are described as "Portable Device Dependent," indicating that the physical connectors vary by laptop manufacturer. The bus interface is PCIe 1.0 x16, providing the data transfer path to the host system.

How It Compares

The FACT PACK lists no nearest rivals for the Quadro FX 350M, and the benchmarks array is empty. The percentile versus all GPUs is 50, placing it at the median of the historical database, but with an average benchmark score of zero, there is no empirical performance data to analyze. In the absence of rival comparisons, the positional analysis relies on the architectural and specification context.

The card's predecessor, the Quadro FX Go, and its successor, the Quadro Fermi-M, bracket its place in the product timeline. Without benchmark scores, the performance delta between these generations cannot be quantified. However, the architectural progression from Curie to the later Fermi-based Quadro line suggests a generational increase in feature support and processing capability, though such an inference is qualitative.

The lack of nearest rivals in the data means that no direct percentage deltas can be cited. The card's position at the 50th percentile of all GPUs in the database is a statistical placeholder, indicating it sits in the middle of the historical distribution, but this is not corroborated by any actual workload performance figures. The data presents a specification sheet rather than a competitive analysis.

FAQ

Q: What is the power consumption of the NVIDIA Quadro FX 350M?

A: The thermal design power (TDP) is specified as 15 W.

Q: Does the Quadro FX 350M support hardware ray tracing?

A: No, the data lists null values for both RT cores and tensor cores, indicating no dedicated hardware for ray tracing or tensor operations.

Q: What is the memory configuration of this graphics card?

A: It features 256 MB of GDDR3 memory on a 128-bit bus, with a memory clock of 450 MHz (900 Mbps effective) and a bandwidth of 14.40 GB/s.

Q: What application programming interfaces (APIs) are supported?

A: The card supports DirectX 9.0c (9_3) and OpenGL 2.1, with no Vulkan support listed.

Q: What process technology is used for the G72 chip?

A: The chip is manufactured on a 90 nm process at TSMC, with a die size of 81 mm² and 112 million transistors.

Q: What is the production status of the Quadro FX 350M?

A: The production status is listed as end-of-life.

Benchmark Performance

The benchmark performance section for the NVIDIA Quadro FX 350M is defined by a complete absence of empirical data. The benchmarks array is empty, and the average benchmark score is explicitly zero. Furthermore, the nearestRivals field is an empty list, precluding any direct comparison with competing products. The only quantitative metric available is the percentile versus all GPUs, which stands at 50.

This 50th percentile figure, in the absence of any raw scores, can only be interpreted as a median placement within the database's historical GPU population. It does not indicate performance parity with any specific card, nor does it provide a baseline for relative speed. The lack of rival data means that any statement regarding performance deltas, such as percentage leads or deficits, is impossible to formulate from the provided facts. The pixel rate of 900.0 MPixel/s and texture rate of 1.800 GTexel/s are the sole performance-related numbers, but they are theoretical maxima rather than application-level results.

Without benchmark scores or rival comparisons, the analytical conclusion is that the Quadro FX 350M's performance cannot be contextualized against its peers using the available data. The specification sheet indicates a low-power, entry-level mobile workstation part, but the measured performance impact of those specifications remains unquantified. The 15 W TDP and 14.40 GB/s bandwidth suggest a constrained environment, but translating that into workload-specific outcomes is not supported by the facts. The data frame is purely descriptive, leaving performance as an unknown variable in the card's profile.