NVIDIA Quadro2 MXR Low Profile

The NVIDIA Quadro2 MXR Low Profile is a professional workstation card built on the Celsius architecture with the NV11B chip, fabricated by TSMC on a 180 nm process with 20 million transistors on a 64 mm² die. It was released on 2000-07-24 and is now end-of-life, positioned between the Quadro Celsius and the Quadro4 Celcius in NVIDIA's professional lineup. The card uses an AGP 4x bus interface and provides a single VGA display output.

Memory Subsystem

The card carries 32 MB of SDR memory on a 128-bit bus, clocked at 183 MHz. This configuration yields a memory bandwidth of 2.928 GB/s. The 128-bit bus is the card's most significant memory asset — it allows the SDR memory to transfer more data per clock cycle than a narrower interface could, partially compensating for the modest 183 MHz memory clock. The 32 MB frame buffer, however, is the defining constraint. At high resolutions, a 32 MB buffer limits the maximum resolution and color depth that can be rendered without falling back to system memory over the AGP 4x link, which is far slower than the dedicated memory bandwidth.

The 800.0 MPixel/s pixel fill rate and 800.0 MTexel/s texture fill rate describe the throughput the memory subsystem must feed. With 4 TMUs and 4 ROPs, the card can process 4 texels per clock and 4 pixels per clock. At low resolutions, the 2.928 GB/s bandwidth is sufficient to keep the 4 TMUs and 4 ROPs busy. But as resolution rises, the 32 MB capacity becomes the binding constraint before bandwidth does — a 32 MB buffer cannot hold large textures or high-depth framebuffers for modern (for the era) resolutions. The SDR memory type, as opposed to a double-data-rate design, means the effective data rate equals the clock rate; there is no doubling. This places a hard ceiling on how much data can be moved for high-resolution scenes. The data shows a card engineered for entry-level workstation use where 32 MB was a common starting point, not a high-end configuration.

Power and Cooling

The FACT PACK does not list a TDP for this card, so no thermal design power figure can be stated. What is documented is a suggested PSU rating of 200 W and a complete absence of power connectors. The card draws all its power from the AGP 4x slot, which simplifies installation in legacy workstations. The single-slot form factor and the low-profile designation indicate a compact physical design intended for space-constrained chassis. The 180 nm process node and 20 million transistor count, with a transistor density of 312.5K per mm², suggest a modest power envelope — though without a TDP figure, this remains qualitative. The 200 W suggested PSU is a system-level recommendation that accounts for the rest of the components, not the card alone; a system with this card would not require a high-capacity power supply. The absence of power connectors means there is no cable routing or connector clearance to plan for. The single-slot cooler is appropriate for the thermal output implied by the 180 nm process, but the pack provides no thermal measurements. As an end-of-life product, these power and cooling characteristics apply only to existing units in legacy systems.

Benchmark Performance

The benchmark data for this card is minimal. The benchmarks array in the FACT PACK is empty, and the average benchmark score is 0. The percentile versus all GPUs is 50, which places the card at the exact median of the database's GPU population. This percentile is the only comparative signal available, but with no recorded benchmark scores, it cannot be tied to specific workload performance. The theoretical peak rates are documented: 800.0 MPixel/s pixel fill and 800.0 MTexel/s texture fill. These are the maximum throughputs the card can sustain under ideal, non-limited conditions. The 4 TMUs and 4 ROPs, together with the 183 MHz memory clock, define the compute ceiling. The DirectX 7.0 and OpenGL 1.2 API support bounds the card's software relevance to the graphics APIs of its release era; it cannot execute modern shader-based workloads. The 0 average score may indicate that no standardized benchmark was run on this card, or that it predates the benchmark suite used by the database. Either way, the data does not support any performance claim beyond the fill rates and the median percentile. The 50th percentile standing suggests the card is neither a high performer nor a low performer relative to the full GPU population in the database, but the empty benchmark array means this percentile is not corroborated by any measured score.

How It Compares

The FACT PACK lists no nearest rivals for this card. The nearestRivals array is empty, so there are no rival names, scores, or deltaPct values to reference. The only comparative context available is the product lineage: the card follows the Quadro Celsius and precedes the Quadro4 Celcius. The data does not include specifications for either the predecessor or the successor, so any comparison must be qualitative. Chronologically, the Quadro2 MXR Low Profile sits between these two generations, released on 2000-07-24. Its 180 nm process and 20 million transistors place it in the early professional Quadro line. The 50th percentile standing among all GPUs is the only numerical comparison point; without rival scores, this percentile cannot be decomposed into per-rival deltas. The absence of rival data means the analysis rests entirely on the card's own specifications. The 32 MB SDR memory and 128-bit bus are the defining features, and they set expectations for capability relative to what the broader database contains. In a database where the card sits at the median, it is neither an outlier on the high end nor on the low end, but the lack of rival entries prevents a more granular positioning. The predecessor and successor names indicate a continuous product line, but their performance characteristics are not documented in this data.

Who Should Consider It

Given the 32 MB frame buffer and 2.928 GB/s bandwidth, this card is suited to low-resolution, low-color-depth workloads. The 800.0 MPixel/s pixel rate and 800.0 MTexel/s texture rate are modest, but they align with the DirectX 7.0 and OpenGL 1.2 APIs the card supports. Users running legacy workstation applications that do not require large frame buffers or high resolutions may find the card adequate. The single VGA output limits it to one display, and the AGP 4x interface means only systems with an AGP slot can use it — PCIe-only systems cannot. The 200 W suggested PSU is a low system requirement, making the card viable for older or low-power workstations. The low-profile single-slot design suits compact or rack-mount chassis. However, for any workload requiring high resolutions or large textures, the 32 MB capacity will be a hard limit. The card's end-of-life status and 2000-07-24 release date mean it is only relevant for retro or legacy systems. The 50th percentile standing suggests it is not a performance outlier; it is a mid-pack card in the database. Users should consider it only if their software targets the DirectX 7.0 / OpenGL 1.2 era and their resolution requirements fit within 32 MB.

FAQ

Q: How much memory does the NVIDIA Quadro2 MXR Low Profile have?

A: It has 32 MB of SDR memory on a 128-bit bus.

Q: What is the memory bandwidth?

A: The memory bandwidth is 2.928 GB/s, based on a 183 MHz memory clock.

Q: Does this card require a power connector?

A: No. The FACT PACK lists no power connectors, and the suggested PSU is 200 W.

Q: What is the pixel fill rate?

A: The pixel fill rate is 800.0 MPixel/s, with a texture fill rate of 800.0 MTexel/s.

Q: What API versions does it support?

A: It supports DirectX 7.0 and OpenGL 1.2.

Q: When was it released, and what is its current status?

A: It was released on 2000-07-24 and is now end-of-life.