AMD Radeon RX 9060 XT LP vs NVIDIA Quadro GP100 Comparison

FAQ

Q: Which GPU has the higher OpenCL benchmark score, the NVIDIA Quadro GP100 or the AMD Radeon RX 9060 XT LP?

A: The AMD Radeon RX 9060 XT LP scores 88,183 in Geekbench OpenCL, while the NVIDIA Quadro GP100 scores 87,445. AMD leads by a narrow 0.8% margin.

Q: How do the two cards compare in memory bandwidth?

A: The NVIDIA Quadro GP100 offers 732.2 GB/s of bandwidth using a 4096-bit HBM2 interface, whereas the AMD Radeon RX 9060 XT LP provides 322.3 GB/s over a 128-bit GDDR6 bus. NVIDIA's bandwidth advantage is substantial, over 2.2 times higher.

Q: What are the transistor counts and die sizes for each GPU?

A: The NVIDIA Quadro GP100 packs 15,300 million transistors on a 610 mm² die (25.1M / mm² density), while the AMD Radeon RX 9060 XT LP integrates 29,700 million transistors on a much smaller 199 mm² die (149.2M / mm² density).

Q: Which GPU supports newer PCIe and display technology?

A: The AMD Radeon RX 9060 XT LP supports PCIe 5.0 x16 and includes 1x HDMI 2.1b plus 2x DisplayPort 2.1a outputs. The NVIDIA Quadro GP100 uses PCIe 3.0 x16 with 1x DVI and 4x DisplayPort 1.4a outputs.

Q: How does the FP32 compute throughput compare?

A: The AMD Radeon RX 9060 XT LP delivers 24.99 TFLOPS of FP32 performance, which is more than double the NVIDIA Quadro GP100's 10.34 TFLOPS.

Q: What is the production status and release timeline for each card?

A: The NVIDIA Quadro GP100 was released on September 30, 2016, and is now end-of-life. The AMD Radeon RX 9060 XT LP was released on December 16, 2025, and remains active in production.

Architecture Differences

The NVIDIA Quadro GP100 and AMD Radeon RX 9060 XT LP represent two vastly different architectural eras. The Quadro GP100 uses the Pascal architecture, built on a 16 nm TSMC process, while the Radeon RX 9060 XT LP leverages RDNA 4.0 on a 4 nm TSMC node. The process node difference is stark: 16 nm versus 4 nm, which explains why AMD can fit 29,700 million transistors onto a 199 mm² die, whereas NVIDIA's older design requires 610 mm² for only 15,300 million transistors. The transistor density figures tell the story clearly: 149.2M / mm² for AMD versus 25.1M / mm² for NVIDIA, a sixfold improvement in packing efficiency.

The memory subsystems are fundamentally different as well. The Quadro GP100 uses 16 GB of HBM2 across a 4096-bit bus, achieving 732.2 GB/s of bandwidth. The Radeon RX 9060 XT LP also has 16 GB of memory, but it is GDDR6 on a 128-bit bus, yielding 322.3 GB/s. The HBM2 stack on NVIDIA is a legacy of its compute-focused workstation design, while AMD's GDDR6 configuration is more conventional for a modern consumer-oriented card. Clock speeds also diverge sharply: the Quadro GP100 runs at a base of 1304 MHz with a boost of 1443 MHz, while the Radeon RX 9060 XT LP has a base of 1380 MHz, a game clock of 2450 MHz, and a boost of 3050 MHz. The AMD card's boost clock is more than double the NVIDIA card's boost, reflecting the efficiency gains of the newer process node.

Feature sets differ in key ways. The Radeon RX 9060 XT LP includes 32 ray tracing cores, a feature entirely absent from the Pascal-based Quadro GP100. The AMD card also supports DirectX 12 Ultimate (12_2) and Vulkan 1.4, while the Quadro GP100 supports DirectX 12 (12_1) and Vulkan 1.3. Both cards offer OpenGL 4.6. The Radeon's FP16 throughput is 24.99 TFLOPS at a 1:1 ratio, matching its FP32 rate, whereas the Quadro GP100's FP16 of 20.69 TFLOPS represents a 2:1 ratio over its FP32 of 10.34 TFLOPS. This indicates the AMD card processes FP16 and FP32 at the same rate, while NVIDIA's Pascal architecture used a different shader arrangement.

Power requirements also reflect the architectural gap. The Quadro GP100 has a TDP of 235 W with a suggested 550 W PSU, while the Radeon RX 9060 XT LP draws only 140 W and recommends a 300 W PSU. Both use a single 8-pin power connector and are dual-slot designs. The AMD card is more power-efficient per unit of compute, but the NVIDIA card's higher bandwidth and older process keep its power draw elevated.

Head-to-Head Benchmarks

The recorded head-to-head data contains a single OpenCL benchmark, and the results are remarkably close. The AMD Radeon RX 9060 XT LP scored 88,183, while the NVIDIA Quadro GP100 scored 87,445. The delta is only 0.8% in favor of AMD, a margin that is nearly negligible in real-world terms. This outcome is somewhat surprising given the architectural differences: the Quadro GP100 has 3584 shading units versus 2048 on the Radeon, and it has a massive memory bandwidth advantage at 732.2 GB/s versus 322.3 GB/s. Yet AMD's much higher clock speeds (3050 MHz boost versus 1443 MHz boost) and newer architecture compensate for the narrower bus and fewer shaders.

The OpenCL workload appears to be sensitive to a combination of raw compute throughput and memory bandwidth. The Quadro GP100's FP32 rate is 10.34 TFLOPS, while the Radeon RX 9060 XT LP reaches 24.99 TFLOPS, a 141% advantage for AMD. Still, the NVIDIA card's 4096-bit memory bus and higher bandwidth might mitigate some of that deficit in memory-bound kernels. The final 0.8% gap suggests that OpenCL performance is balanced between these two very different designs. The database also records that the Quadro GP100's nearest rivals include the AMD Radeon PRO W7600 (87,108, 0.4% slower) and the NVIDIA RTX A4500 (91,671, 4.6% faster), while the Radeon RX 9060 XT LP's nearest rivals include the NVIDIA CMP 30HX (63,842, 0% delta) and the AMD Radeon Pro Vega 56 (63,693, 0.2% slower). The Radeon's average benchmark score across multiple tests is 63,830, which is dragged down by its Vulkan score of 39,476, while its OpenCL score of 88,183 is competitive with the Quadro GP100's 87,445.

Specification Differences

The two GPUs diverge on nearly every specification field. The NVIDIA Quadro GP100 uses the GP100 chip with Pascal architecture, while the AMD Radeon RX 9060 XT LP uses the Navi 44 chip with RDNA 4.0. The process nodes are 16 nm versus 4 nm. Transistor counts are 15,300 million versus 29,700 million, and die sizes are 610 mm² versus 199 mm². The shading units differ: 3584 on NVIDIA versus 2048 on AMD. Texture mapping units are 224 versus 128, and ROPs are 96 versus 64. The AMD card has 32 ray tracing cores; the NVIDIA card has none.

Memory configurations differ significantly: both have 16 GB, but the Quadro GP100 uses HBM2 with a 4096-bit bus and 732.2 GB/s bandwidth, while the Radeon RX 9060 XT LP uses GDDR6 with a 128-bit bus and 322.3 GB/s bandwidth. Clock speeds: the Quadro GP100 has a 1304 MHz base and 1443 MHz boost, whereas the Radeon RX 9060 XT LP has a 1380 MHz base, 2450 MHz game clock, and 3050 MHz boost. Memory clocks are 715 MHz (1430 Mbps effective) for NVIDIA versus 2518 MHz (20.1 Gbps effective) for AMD.

Compute rates: pixel rate is 138.5 GPixel/s for NVIDIA versus 195.2 GPixel/s for AMD. Texture rate is 323.2 GTexel/s versus 390.4 GTexel/s. FP32 is 10.34 TFLOPS versus 24.99 TFLOPS. FP16 is 20.69 TFLOPS (2:1) versus 24.99 TFLOPS (1:1). TDP is 235 W versus 140 W. Suggested PSU is 550 W versus 300 W. Bus interface is PCIe 3.0 x16 versus PCIe 5.0 x16. Display outputs are 1x DVI and 4x DisplayPort 1.4a versus 1x HDMI 2.1b and 2x DisplayPort 2.1a. DirectX support is 12 (12_1) versus 12 Ultimate (12_2). Vulkan is 1.3 versus 1.4. The Quadro GP100 is end-of-life with a 2016 release date, while the Radeon RX 9060 XT LP is active with a 2025 release date. The Quadro's dimensions are 267 mm (10.5 inches) in length and 111 mm (4.4 inches) in height; the Radeon's dimensions are not recorded.

Where Each One Wins

The AMD Radeon RX 9060 XT LP wins in raw compute throughput. Its FP32 performance of 24.99 TFLOPS is 2.4 times that of the Quadro GP100's 10.34 TFLOPS. It also leads in pixel rate (195.2 GPixel/s versus 138.5 GPixel/s) and texture rate (390.4 GTexel/s versus 323.2 GTexel/s). The AMD card's ray tracing cores provide hardware-accelerated ray tracing that the Pascal-based NVIDIA card cannot perform at all. It also supports newer API standards: DirectX 12 Ultimate and Vulkan 1.4 versus DirectX 12_1 and Vulkan 1.3. The AMD card is more power-efficient, drawing 140 W versus 235 W, and it has a higher boost clock at 3050 MHz versus 1443 MHz. The single head-to-head OpenCL benchmark also goes to AMD, albeit by a slim 0.8% margin.

The NVIDIA Quadro GP100 wins in memory bandwidth and capacity configuration. Its 732.2 GB/s bandwidth is more than double the AMD card's 322.3 GB/s, and the 4096-bit HBM2 bus is a legacy workstation advantage that the 128-bit GDDR6 bus cannot match. The Quadro GP100 also has more shading units (3584 versus 2048) and more ROPs (96 versus 64), which can benefit certain compute workloads that scale with shader count rather than clocks. Its FP16 throughput of 20.69 TFLOPS is lower than AMD's 24.99 TFLOPS, but the 2:1 ratio means it can accelerate FP16 tasks relative to its own FP32. The NVIDIA card also offers a DVI output, which may be relevant for legacy display connections, and its 267 mm length is a specific physical dimension that may fit certain chassis constraints.

The Verdict

The benchmark data indicates a clear split in use cases. For compute workloads that rely on raw FP32 throughput, modern API features, and ray tracing, the AMD Radeon RX 9060 XT LP is the stronger choice. It delivers 24.99 TFLOPS of FP32, supports DirectX 12 Ultimate and Vulkan 1.4, includes 32 ray tracing cores, and does so at a lower 140 W TDP. Its OpenCL score of 88,183 edges out the Quadro GP100's 87,445, and its nearest rivals in the database (NVIDIA CMP 30HX at 63,842, AMD Radeon RX 7600M at 63,775) are far behind its OpenCL result. The Radeon is also an active product with a 2025 release, meaning ongoing driver support and availability.

For workloads that depend on memory bandwidth, large memory bus widths, or legacy display outputs, the NVIDIA Quadro GP100 remains relevant. Its 732.2 GB/s bandwidth and 4096-bit HBM2 interface are unmatched by the AMD card, and its 3584 shading units provide parallel processing headroom. The Quadro GP100's nearest rivals include the AMD Radeon PRO W7600 (87,108, 0.4% behind) and the NVIDIA RTX A4500 (91,671, 4.6% ahead), placing it in a competitive workstation tier despite its age. However, its 235 W power draw, PCIe 3.0 interface, and end-of-life status are significant drawbacks. The data suggests that the AMD Radeon RX 9060 XT LP is the better all-around performer for modern compute tasks, while the Quadro GP100 is a specialized bandwidth-oriented card for specific legacy or memory-bound scenarios. The 0.8% OpenCL gap is too small to declare a definitive winner on that metric alone, but the AMD card's broader feature set and higher compute rates tip the overall balance in its favor.