AMD Radeon RX 9060 XT LP vs NVIDIA Quadro P6000 Comparison

# The Verdict

The data presents a stark generational split. The AMD Radeon RX 9060 XT LP wins decisively in OpenCL compute, posting 88,183 points against the NVIDIA Quadro P6000’s 66,382—a 24.7% advantage. This is the newer card’s strongest statement: its 24.99 TFLOPS FP32 throughput and 24.99 TFLOPS FP16 (1:1) capability dwarf the Quadro’s 12.63 TFLOPS FP32 and severely limited 197.4 GFLOPS FP16 (1:64). For any workload that leans on raw shader math or half-precision, the RX 9060 XT LP is the only rational choice.

However, the NVIDIA Quadro P6000 strikes back in Vulkan, scoring 73,590 versus the AMD’s 39,476—an 86.4% margin. This is not a small gap; it is a near-doubling of performance in the API that often governs game compatibility and certain professional visualization stacks. The Quadro’s 24 GB of GDDR5X on a 384-bit bus (432.8 GB/s) also provides 8 GB more capacity and 110.5 GB/s more bandwidth than the RX 9060 XT LP’s 16 GB GDDR6 on a 128-bit bus (322.3 GB/s). That memory advantage is critical for large datasets that exceed 16 GB.

Who should pick which? Data centers or workstations running OpenCL-heavy compute, machine-learning inference with FP16, or modern RDNA-optimized code should choose the AMD Radeon RX 9060 XT LP. It is also the only card with hardware ray tracing (32 RT cores), a 4 nm process, and PCIe 5.0 x16 interface. Conversely, legacy Vulkan applications, DVI-based display setups, or workloads requiring more than 16 GB of framebuffer will find the NVIDIA Quadro P6000 superior. The Quadro’s 90th percentile ranking versus the AMD’s 89th is a statistical tie, but the average benchmark score (69,986 vs 63,830) slightly favors NVIDIA—a result driven entirely by the Vulkan blowout.

The production status seals the practical verdict: the Quadro P6000 is end-of-life (released 2016), while the RX 9060 XT LP is active (released 2025). For new deployments, the AMD card is the forward-looking pick unless a specific Vulkan or VRAM requirement dictates otherwise.

FAQ

Q: Which card has higher raw compute throughput?

A: The AMD Radeon RX 9060 XT LP delivers 24.99 TFLOPS FP32 and 24.99 TFLOPS FP16 (1:1), versus the NVIDIA Quadro P6000’s 12.63 TFLOPS FP32 and 197.4 GFLOPS FP16 (1:64). That is a 24.7% higher OpenCL score for AMD (88,183 vs 66,382).

Q: Why does the NVIDIA card win in Vulkan despite lower compute?

A: Benchmark results show the Quadro P6000 scores 73,590 in Geekbench Vulkan, which is 86.4% higher than the RX 9060 XT LP’s 39,476. This suggests NVIDIA’s Pascal architecture has more mature Vulkan driver optimization or different scheduling characteristics that favor that API.

Q: Which card has more memory and bandwidth?

A: The NVIDIA Quadro P6000 has 24 GB of GDDR5X on a 384-bit bus, yielding 432.8 GB/s. The AMD Radeon RX 9060 XT LP has 16 GB of GDDR6 on a 128-bit bus, yielding 322.3 GB/s. The Quadro provides 8 GB more capacity and roughly 34% more bandwidth.

Q: Does the AMD card support ray tracing?

A: Yes, the AMD Radeon RX 9060 XT LP includes 32 dedicated RT cores. The NVIDIA Quadro P6000 has no RT cores listed. This makes the AMD card the only one with hardware-accelerated ray tracing capability.

Q: What are the power and interface differences?

A: The AMD card has a 140 W TDP and requires a 300 W suggested PSU, while the NVIDIA card has a 250 W TDP and requires a 600 W suggested PSU. The AMD card uses PCIe 5.0 x16, whereas the NVIDIA card uses PCIe 3.0 x16.

Q: Which card is still in production?

A: The AMD Radeon RX 9060 XT LP is marked as Active production status, released 2025-12-16. The NVIDIA Quadro P6000 is End-of-life, released 2016-09-30, with its successor designated as Quadro Volta.

Architecture Differences

The two cards represent fundamentally different eras of GPU design. The NVIDIA Quadro P6000 uses the GP102 chip on the Pascal architecture, fabricated on TSMC’s 16 nm process. It packs 11,800 million transistors into a 471 mm² die, yielding a transistor density of 25.1M / mm². The Pascal generation is a mature, high-bandwidth design focused on maximizing memory throughput and rasterization.

The AMD Radeon RX 9060 XT LP uses the Navi 44 chip on RDNA 4.0, fabricated on TSMC’s 4 nm process. It contains 29,700 million transistors in a 199 mm² die—a density of 149.2M / mm². That is a 5.9x improvement in transistor density, enabling the AMD card to fit more than double the transistors in less than half the die area. RDNA 4.0 introduces 32 RT cores, which the Pascal architecture lacks entirely.

The FP16 story is particularly telling. The Quadro P6000’s FP16 throughput is 197.4 GFLOPS, a 1:64 ratio to its FP32 rate—indicating that half-precision is severely de-emphasized. The RX 9060 XT LP achieves 24.99 TFLOPS FP16 at a 1:1 ratio, meaning it can process half-precision at the same rate as full precision. This is a fundamental architectural shift that matters for AI inference, where FP16 is the working precision.

Display outputs also differ. The Quadro P6000 offers 1x DVI and 4x DisplayPort 1.4a, while the RX 9060 XT LP provides 1x HDMI 2.1b and 2x DisplayPort 2.1a. The AMD card supports newer display standards, including the higher bandwidth of DisplayPort 2.1a.

Specification Differences

The two cards diverge across nearly every measurable specification. The NVIDIA Quadro P6000 has 3,840 shading units, 240 TMUs, and 96 ROPs, while the AMD Radeon RX 9060 XT LP has 2,048 shading units, 128 TMUs, and 64 ROPs. Despite having fewer execution units, the AMD card achieves higher pixel rate (195.2 GPixel/s vs 157.9 GPixel/s) and nearly identical texture rate (390.4 GTexel/s vs 394.8 GTexel/s), thanks to its 3,050 MHz boost clock versus the Quadro’s 1,645 MHz.

Clocks reveal the process advantage. The Quadro P6000 runs at 1,506 MHz base and 1,645 MHz boost, with memory at 1,127 MHz (9 Gbps effective). The RX 9060 XT LP runs at 1,380 MHz base, 2,450 MHz game clock, and 3,050 MHz boost, with memory at 2,518 MHz (20.1 Gbps effective). The AMD card’s boost clock is nearly double the NVIDIA’s.

Memory configuration is a clear split: 24 GB GDDR5X on 384-bit for NVIDIA versus 16 GB GDDR6 on 128-bit for AMD. Bandwidth favors NVIDIA at 432.8 GB/s vs 322.3 GB/s. Power consumption is dramatically lower on AMD: 140 W TDP with a 300 W suggested PSU, versus 250 W TDP with a 600 W suggested PSU. Both use a single 8-pin power connector and dual-slot cooling.

Bus interface favors AMD with PCIe 5.0 x16 versus PCIe 3.0 x16. API support also differs: AMD supports DirectX 12 Ultimate (12_2), while NVIDIA supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4. Physical dimensions are only listed for the NVIDIA card: 267 mm length, 111 mm height. The AMD card’s dimensions are not specified in the data.

Head-to-Head Benchmarks

The benchmark suite consists of two Geekbench tests, and each card wins one. The AMD Radeon RX 9060 XT LP takes the OpenCL test with 88,183 points against the NVIDIA Quadro P6000’s 66,382. The delta is 24.7% in AMD’s favor. This is the larger of the two wins in absolute percentage terms, and it aligns with the AMD card’s 2x advantage in FP32 and 126x advantage in FP16 compute.

The NVIDIA Quadro P6000 wins the Vulkan test with 73,590 points against the AMD’s 39,476. The delta is 86.4% in NVIDIA’s favor—a dominant margin that cannot be explained by any single spec. The Quadro’s higher memory bandwidth (432.8 GB/s vs 322.3 GB/s) may contribute, but the gap suggests a significant API-level efficiency difference. In fact, the AMD card’s Vulkan score (39,476) is lower than its own OpenCL score (88,183), while the NVIDIA card’s Vulkan score (73,590) is higher than its OpenCL score (66,382). This cross-API behavior is unusual and points to architectural strengths and weaknesses.

The average benchmark scores reflect these splits. The Quadro P6000 averages 69,986, placing it in the 90th percentile of all GPUs. The RX 9060 XT LP averages 63,830, placing it in the 89th percentile. The rival analysis shows the Quadro sitting near the AMD Radeon Pro WX 8200 (69,870, +0.2%) and NVIDIA RTX A3000 Mobile (70,140, -0.2%). The RX 9060 XT LP sits near the NVIDIA CMP 30HX (63,842, 0% delta) and AMD Radeon RX 7600M (63,775, +0.1%).

The wins are evenly split at 1-1, but the magnitude matters. The AMD’s 24.7% OpenCL victory is substantial, yet the NVIDIA’s 86.4% Vulkan victory is overwhelming. For any unified benchmark score, the Quadro’s Vulkan dominance drags the average up, while the AMD card’s poor Vulkan showing drags its average down. This is the single most important takeaway: the RX 9060 XT LP is a compute monster that stumbles on Vulkan, while the Quadro P6000 remains a Vulkan specialist despite its age. Buyers must match the card to the API their software actually uses.