NVIDIA Quadro FX 370
NVIDIA graphics card specifications and benchmark scores
At a Glance
NVIDIANVIDIA Quadro FX 370 Specifications
GPU Core
Shader units and compute resources
The NVIDIA Quadro FX 370 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.
Quadro FX 370 Clock Speeds
GPU and memory frequencies
Clock speeds directly impact the Quadro FX 370'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 Quadro FX 370 by NVIDIA dynamically adjusts frequencies based on workload, temperature, and power limits to maximize performance while maintaining stability.
NVIDIA's Quadro FX 370 Memory
VRAM capacity and bandwidth
VRAM (Video RAM) is dedicated memory for storing textures, frame buffers, and shader data. The Quadro FX 370'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.
Quadro FX 370 by NVIDIA Cache
On-chip cache hierarchy
On-chip cache provides ultra-fast data access for the Quadro FX 370, 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.
Quadro FX 370 Theoretical Performance
Compute and fill rates
Theoretical performance metrics provide a baseline for comparing the NVIDIA Quadro FX 370 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.
Tesla Architecture & Process
Manufacturing and design details
The NVIDIA Quadro FX 370 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 Quadro FX 370 will perform in GPU benchmarks compared to previous generations.
Power & Thermal
TDP and power requirements
Power specifications for the NVIDIA Quadro FX 370 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 Quadro FX 370 to maintain boost clocks without throttling.
Quadro FX 370 by NVIDIA Physical & Connectivity
Dimensions and outputs
Physical dimensions of the NVIDIA Quadro FX 370 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.
NVIDIA API Support
Graphics and compute APIs
API support determines which games and applications can fully utilize the NVIDIA Quadro FX 370. 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.
Quadro FX 370 Product Information
Release and pricing details
The NVIDIA Quadro FX 370 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 Quadro FX 370 by NVIDIA represents good value at current market prices. Predecessor and successor information aids in tracking generational improvements and planning future upgrades.
About NVIDIA Quadro FX 370
The NVIDIA Quadro FX 370 is an end-of-life professional graphics card built on the 80 nm Tesla architecture, using the G84 chip with 289 million transistors on a 169 mm² die. It targets entry-level workstation duties with a 256 MB DDR2 memory buffer on a 64-bit bus, delivering 8.000 GB/s of bandwidth. With a 35 W TDP and no auxiliary power connectors, it is a low-footprint option for legacy systems, though its benchmark presence is minimal—holding a 50th percentile position among all GPUs, with an average benchmark score of 0 and no recorded nearest rivals in the database.
Benchmark Performance
The Quadro FX 370’s compute specifications are modest by any modern standard, and the data reflects that. The card features 16 shading units, 8 texture mapping units, and 4 raster output units. Its pixel rate is 1.440 GPixel/s, while the texture rate stands at 2.880 GTexel/s. Floating-point performance is listed at 23.04 GFLOPS for FP32 operations. These figures place the card firmly in the entry-level segment of its era, but without any benchmark scores or nearestRivals entries in the fact pack, direct percentage comparisons to contemporaries are unavailable. The 50th percentile rank among all GPUs suggests it sat in the middle of the performance distribution at the time of its release, but the average benchmark score of 0 indicates that no standardized test results have been captured for it in this database.
What the numbers do show is a balanced allocation of resources for a 2007-era workstation card. The 16:8:4 ratio of shaders to TMUs to ROPs is typical for a low-cost G84 derivative, prioritizing geometry throughput over fill-rate-heavy workloads. The memory clock runs at 500 MHz, translating to 1000 Mbps effective, which combined with the 64-bit bus yields 8.000 GB/s—enough for basic CAD viewport rendering but far below the bandwidth of even mid-range consumer cards of that generation. The FP32 throughput of 23.04 GFLOPS is roughly in line with other Tesla-architecture entries, but the lack of rival data means the analysis must rely on absolute values rather than deltas.
For practical purposes, the benchmark results indicate this card is suitable for 2D desktop acceleration and very light 3D tasks, such as rotating simple models or viewing non-textured wireframes. Anything requiring heavy shader work or large texture sets will quickly exceed the 256 MB frame buffer and 8.000 GB/s bandwidth. The 50th percentile rank is only a positional marker; it does not imply competitive performance against later GPUs, as the database includes all generations. Users should interpret the 23.04 GFLOPS figure as a hard ceiling for compute workloads—modern integrated graphics surpass this by orders of magnitude, but within the confines of the fact pack, no such comparison exists.
Ray Tracing and Feature Set
The Quadro FX 370 has no dedicated ray tracing cores and no tensor cores, as those technologies were not part of the Tesla architecture. The fact pack explicitly lists both fields as null, confirming their absence. Instead, the card relies on the traditional rasterization pipeline of the G84 chip. For API support, the card offers DirectX 11.1 (feature level 10_0) and OpenGL 3.3. DirectX 11.1 support is notable because the card’s hardware predates that API—it is a software compatibility layer that maps DX11 calls down to the DX10 feature set. Vulkan support is not listed, meaning it is absent or untested.
The feature set is thus limited to what the Tesla architecture could provide: fixed-function texture filtering, early-z rejection, and programmable shaders via the 16 unified units. There is no hardware-accelerated ray tracing, no mesh shaders, and no variable-rate shading. For professional software, OpenGL 3.3 is the more relevant API, supporting modern (for the time) shader models and geometry shaders, but it falls short of later revisions that added tessellation and compute shaders. The display outputs are limited to 2x DVI, with no DisplayPort or HDMI, which constrains modern monitor connectivity without adapters.
The lack of RT and tensor cores means any workload involving real-time ray tracing, AI denoising, or deep learning inference is entirely unsupported. The card’s 16 shading units would be overwhelmed by even a single ray-traced scene, and the 8.000 GB/s bandwidth would become a bottleneck for any BVH traversal data. In a professional context, this card is strictly for legacy software that predates ray tracing, such as early 2000s CAD packages or 2D drafting tools. The DirectX 11.1 (10_0) support is a quirk—it allows the card to run some newer applications in compatibility mode, but performance will be poor due to the hardware limitations.
Power and Cooling
The Quadro FX 370 has a TDP of 35 W, making it one of the lowest-power discrete GPUs ever produced. This figure is remarkably low, even for the 80 nm process node, and it directly influences the cooling and power delivery requirements. The card is single-slot in width, with a length of 198 mm (7.8 inches) and a height of 111 mm (4.4 inches). It requires no auxiliary power connectors—the fact pack explicitly lists “None” for power connectors—so all power is drawn from the PCIe 1.0 x16 slot itself. The suggested PSU rating is 200 W, which is a conservative recommendation that accounts for the rest of a system’s components, not just the GPU.
Thermal management is straightforward. A single-slot cooler, likely a low-profile heatsink with a small fan, is sufficient for 35 W of heat output. The card’s dimensions allow it to fit in most compact chassis, and the absence of power connectors means no cable management is needed. For a workstation from 2007, this was a plug-and-play solution: insert into any PCIe slot, install drivers, and run. The 200 W suggested PSU is not a strict requirement for the card alone—any power supply from that era with a working PCIe slot would suffice—but the recommendation ensures stability for the CPU, drives, and other peripherals.
In modern systems, the 35 W TDP is negligible. A contemporary PSU of any wattage will easily handle it, but the PCIe 1.0 x16 interface may not be compatible with newer motherboards that have moved to PCIe 3.0 or 4.0 slots, though backward compatibility is usually maintained. The single-slot design and lack of connectors mean installation is trivial, but the card’s end-of-life status and old drivers may pose software compatibility challenges on current operating systems. Cooling is a non-issue; passive cooling might even suffice given the low TDP, but the fact pack does not specify the cooler type beyond single-slot.
FAQ
Q: What is the memory size and type on the Quadro FX 370?
A: The card has 256 MB of DDR2 memory on a 64-bit bus, providing 8.000 GB/s of bandwidth.
Q: Does the Quadro FX 370 support ray tracing?
A: No. The card has no ray tracing cores or tensor cores; it relies solely on the Tesla architecture’s traditional rasterization pipeline.
Q: What power supply is recommended for this card?
A: The suggested PSU rating is 200 W. The card itself draws 35 W and requires no auxiliary power connectors, drawing power entirely from the PCIe 1.0 x16 slot.
Q: What APIs does the Quadro FX 370 support?
A: It supports DirectX 11.1 (feature level 10_0) and OpenGL 3.3. Vulkan is not listed as supported.
Q: How many display outputs does the card have?
A: The Quadro FX 370 provides 2x DVI outputs, with no other display connectors listed.
Q: When was the Quadro FX 370 released, and what is its production status?
A: It was released on 2007-09-11 and is currently marked as end-of-life.
How It Compares
The nearestRivals list in the fact pack is empty, so there are no direct competitor scores or percentage deltas to reference. This absence is itself informative: the Quadro FX 370 was a low-volume professional card, and benchmark databases typically do not capture results for such niche products. Without rival data, the comparison must be made against the absolute metrics in the fact pack. Its 50th percentile rank among all GPUs suggests it outperformed half of the GPUs in the database—but that includes obsolete integrated graphics and ancient accelerators, so the percentile is not a meaningful measure of contemporary competition.
If one were to position it against the broader Tesla generation, the card’s 16 shading units and 23.04 GFLOPS place it at the bottom of that architecture’s stack. The 256 MB memory and 64-bit bus are the smallest configurations found in any discrete GPU from that era. The lack of rivals in the data means no percentage deltas can be stated; the analysis must rely on the card’s own specifications. The 35 W TDP is its most distinctive feature, making it more power-efficient than any card with similar performance from its time, but that advantage is irrelevant for modern workloads.
The empty nearestRivals also indicates that the database has no comparable products to benchmark against—likely because the card’s performance was so low that it fell outside the testing range of most review sites. In practice, any card from the same era with a 128-bit memory bus or more than 16 shading units would outperform it, but those figures are not in the fact pack and cannot be cited. The card’s position is thus defined by its own numbers: a 50th percentile rank, a 0 average benchmark score, and no recorded rivals.
Who Should Consider It
The Quadro FX 370 is a card for a very specific use case: running legacy professional software on an old system that requires a certified workstation GPU but has minimal performance needs. The 256 MB memory and 8.000 GB/s bandwidth are sufficient for 2D CAD drafting, simple schematic viewing, or spreadsheet-heavy workflows with multiple monitors via the 2x DVI outputs. The 23.04 GFLOPS FP32 performance can handle basic 3D rotation and panning in OpenGL 3.3 applications, but any scene with complex lighting, high polygon counts, or large textures will cause stuttering or out-of-memory errors.
For resolution-based recommendations, the card is only viable at 1080p or lower—and even then, only for 2D or very light 3D workloads. At 1440p or 4K, the 8.000 GB/s bandwidth and 4 ROPs would result in unacceptably low frame rates, even for desktop rendering. The DirectX 11.1 (10_0) support means some modern 2D applications might run, but the 16 shading units will struggle with any shader-heavy interface effects. The 35 W TDP and lack of power connectors make it ideal for a low-power server or a headless workstation where only basic display output is needed.
The card’s 50th percentile rank and 0 average benchmark score suggest it is not a performance part by any measure. It is a compatibility part, designed for software certification rather than speed. If your workload involves the exact era of CAD or GIS software that was certified for the Quadro FX 370, and you have a motherboard with a PCIe 1.0 x16 slot, this card will function as intended. For anything demanding more than 23.04 GFLOPS or 8.000 GB/s of bandwidth, the data shows it is inadequate. The launch MSRP was 129 USD, but its end-of-life status means it should only be considered for historical or legacy systems, not new builds.
Detailed benchmark scores and charts for the NVIDIA Quadro FX 370 are below.
Benchmark Scores
No benchmark data available for this GPU.
Compare with Other GPUs
Select another GPU to compare specifications and benchmarks side-by-side.
Browse GPUs