AMD Radeon RX 9060 vs NVIDIA P106-090 Comparison

FAQ

Q: How does the AMD Radeon RX 9060 compare to the NVIDIA P106-090 in average benchmark score?

A: The AMD Radeon RX 9060 has an average benchmark score of 16014, while the NVIDIA P106-090 scores 13470. This puts the RX 9060 roughly 18.9% ahead of the P106-090 in overall average performance.

Q: Which card has the higher percentile ranking among all GPUs?

A: The AMD Radeon RX 9060 sits in the 59th percentile of all GPUs, which is higher than the NVIDIA P106-090's 54th percentile. The 5-percentage-point gap indicates the RX 9060 outperforms a larger share of the GPU population.

Q: What is the most significant performance difference in the head-to-head tests?

A: The largest delta appears in 3DMark Steel Nomad DX12, where the RX 9060 scores 3322 versus the P106-090's 509, a 552.7% advantage. This represents the most lopsided result across all recorded benchmarks.

Q: Are there any benchmark tests where the NVIDIA P106-090 wins?

A: No. In the three head-to-head tests recorded (3DMark Steel Nomad DX12, Geekbench OpenCL, and Geekbench Vulkan), the AMD Radeon RX 9060 wins all three. The recorded data shows 3 wins for the RX 9060 and 0 for the P106-090.

Q: What is the memory configuration difference between these two cards?

A: The RX 9060 uses 8 GB of GDDR6 memory on a 128-bit bus with 288.0 GB/s bandwidth. The P106-090 uses 3 GB of GDDR5 memory on a 192-bit bus with 192.2 GB/s bandwidth. The RX 9060 has substantially more capacity and higher bandwidth despite a narrower bus.

Q: Which card has more shading units and texture mapping units?

A: The AMD Radeon RX 9060 features 1792 shading units and 112 TMUs, compared to the NVIDIA P106-090's 768 shading units and 48 TMUs. The RX 9060 has more than double the shading units and TMUs of the P106-090.

Architecture Differences

The AMD Radeon RX 9060 is built on the RDNA 4.0 architecture with the Navi 44 chip, fabricated on a 4 nm process at TSMC. This is a stark contrast to the NVIDIA P106-090, which uses the Pascal architecture with the GP106 chip on a 16 nm process, also from TSMC. The process node difference is significant: 4 nm versus 16 nm represents multiple generations of manufacturing advancement, which directly influences transistor density and power efficiency.

The transistor counts illustrate this gap clearly. The RX 9060 packs 29,700 million transistors into a 199 mm² die, yielding a density of 149.2 million transistors per square millimeter. The P106-090 has only 4,400 million transistors on a 200 mm² die, for a density of 22.0 million per square millimeter. Despite nearly identical die sizes, the RX 9060 crams nearly seven times more transistors into the same physical area, a direct result of the newer process node.

Clock speeds also differ substantially. The RX 9060 runs a base clock of 1700 MHz, a game clock of 2400 MHz, and a boost clock of 2990 MHz. The P106-090 has a base clock of 1354 MHz and a boost clock of 1531 MHz. The RX 9060's boost clock is nearly double that of the P106-090's, contributing to its massive compute advantage.

The RX 9060 supports DirectX 12 Ultimate (12_2), while the P106-090 is limited to DirectX 12 (12_1). Both cards support OpenGL 4.6 and Vulkan 1.4, so API compatibility is similar except for the newer DirectX feature level on the AMD side. The RX 9060 also includes 28 ray tracing cores, whereas the P106-090 has no ray tracing cores at all, making it a legacy architecture in that regard.

The memory subsystems are fundamentally different as well. The RX 9060 uses 8 GB of GDDR6 at 2250 MHz (18 Gbps effective) on a 128-bit bus, delivering 288.0 GB/s of bandwidth. The P106-090 uses 3 GB of GDDR5 at 2002 MHz (8 Gbps effective) on a 192-bit bus, delivering 192.2 GB/s. The RX 9060 has more than double the memory capacity and about 50% more bandwidth.

Power and interface specifications highlight the generational divide. The RX 9060 has a TDP of 132 W, uses a single 8-pin power connector, and requires a 300 W suggested PSU. It connects via PCIe 5.0 x16. The P106-090 has a 75 W TDP, a single 6-pin connector, a 250 W suggested PSU, and uses a PCIe 1.0 x1 interface, which is an extremely narrow connection that severely limits data transfer. Notably, the P106-090 has no display outputs, making it a dedicated compute or mining card, while the RX 9060 offers 1x HDMI 2.1b and 2x DisplayPort 2.1a outputs.

Head-to-Head Benchmarks

The recorded head-to-head data covers three benchmark tests, and the AMD Radeon RX 9060 wins all of them decisively. The most dramatic result is in 3DMark Steel Nomad DX12, where the RX 9060 scores 3322 against the P106-090's 509. This represents a 552.7% advantage for the AMD card, meaning it delivers more than six times the performance in this modern DirectX 12 workload. The P106-090's age and lack of modern feature support are clearly exposed in this test.

In Geekbench OpenCL, the RX 9060 scores 88183 while the P106-090 manages 21304. The delta here is 313.9%, putting the AMD card at roughly four times the compute performance of the NVIDIA card. OpenCL is a compute-oriented workload, and the RX 9060's 21.43 TFLOPS of FP32 throughput versus the P106-090's 2.352 TFLOPS explains this large gap. The FP16 comparison is even more extreme: the RX 9060 delivers 21.43 TFLOPS at a 1:1 ratio, while the P106-090 manages only 36.74 GFLOPS at a 1:64 ratio.

The Geekbench Vulkan test shows a narrower but still substantial margin. The RX 9060 scores 39476, and the P106-090 scores 18596, a 112.3% advantage. This means the RX 9060 is roughly double the performance of the P106-090 in Vulkan graphics workloads. The smaller delta here compared to the other tests suggests that the P106-090's Pascal architecture still has some relevance in Vulkan, though it remains firmly behind.

Across all three tests, the RX 9060's wins are decisive. The smallest margin is 112.3%, and the largest is 552.7%. There is no benchmark in the recorded data where the P106-090 comes close to parity. The pattern is consistent: the newer RDNA 4.0 architecture dominates the older Pascal architecture in every measured workload.

The Verdict

The data points to a clear conclusion: the AMD Radeon RX 9060 is the superior card by a wide margin. In the head-to-head benchmarks, it wins all three tests with deltas ranging from 112.3% to 552.7%. Its average benchmark score of 16014 places it in the 59th percentile of all GPUs, while the P106-090's 13470 average places it in the 54th percentile. The RX 9060 also holds a higher position relative to its nearest rivals, with an average score that is only 0.7% below the NVIDIA GeForce RTX 3060 Ti.

For users considering the RX 9060, the architecture alone justifies the choice. It features ray tracing cores, a modern 4 nm process, DirectX 12 Ultimate support, and 8 GB of GDDR6 memory. The P106-090, by contrast, is an end-of-life product from 2017 with a 16 nm process, no ray tracing support, only 3 GB of GDDR5 memory, and no display outputs. Its PCIe 1.0 x1 interface is a severe bottleneck that would limit performance even in systems where it could be installed.

The P106-090's only advantage lies in power consumption, with a 75 W TDP versus the RX 9060's 132 W. For compute workloads where power draw is the primary constraint and display output is unnecessary, the P106-090 could theoretically be used in a low-power mining or compute farm. However, its performance is so far behind that any efficiency advantage is negated by the sheer amount of work the RX 9060 completes in the same time.

The verdict is straightforward: the AMD Radeon RX 9060 is the recommended choice for virtually any use case. The NVIDIA P106-090 is a legacy mining card with limited applicability and no path to modern gaming or professional workloads.

Specification Differences

Process Node: AMD Radeon RX 9060 uses 4 nm; NVIDIA P106-090 uses 16 nm.

Transistors: RX 9060 has 29,700 million; P106-090 has 4,400 million.

Transistor Density: RX 9060 has 149.2M / mm²; P106-090 has 22.0M / mm².

Base Clock: RX 9060 runs at 1700 MHz; P106-090 at 1354 MHz.

Boost Clock: RX 9060 reaches 2990 MHz; P106-090 reaches 1531 MHz.

Memory Size: RX 9060 has 8 GB GDDR6; P106-090 has 3 GB GDDR5.

Memory Bus Width: RX 9060 uses 128 bit; P106-090 uses 192 bit.

Memory Bandwidth: RX 9060 delivers 288.0 GB/s; P106-090 delivers 192.2 GB/s.

Shading Units: RX 9060 has 1792; P106-090 has 768.

TMUs: RX 9060 has 112; P106-090 has 48.

ROPs: RX 9060 has 64; P106-090 has 48.

Ray Tracing Cores: RX 9060 has 28; P106-090 has none.

Pixel Rate: RX 9060 achieves 191.4 GPixel/s; P106-090 achieves 73.49 GPixel/s.

Texture Rate: RX 9060 achieves 334.9 GTexel/s; P106-090 achieves 73.49 GTexel/s.

FP32 Performance: RX 9060 delivers 21.43 TFLOPS; P106-090 delivers 2.352 TFLOPS.

FP16 Performance: RX 9060 delivers 21.43 TFLOPS (1:1); P106-090 delivers 36.74 GFLOPS (1:64).

TDP: RX 9060 is rated at 132 W; P106-090 at 75 W.

Power Connectors: RX 9060 uses 1x 8-pin; P106-090 uses 1x 6-pin.

Suggested PSU: RX 9060 recommends 300 W; P106-090 recommends 250 W.

Bus Interface: RX 9060 uses PCIe 5.0 x16; P106-090 uses PCIe 1.0 x1.

Display Outputs: RX 9060 has 1x HDMI 2.1b and 2x DisplayPort 2.1a; P106-090 has no outputs.

DirectX Support: RX 9060 supports 12 Ultimate (12_2); P106-090 supports 12 (12_1).

Production Status: RX 9060 is Active; P106-090 is End-of-life.

Where Each One Wins

The AMD Radeon RX 9060 wins in every recorded benchmark category. In 3DMark Steel Nomad DX12, it outperforms the P106-090 by 552.7%, making it the clear choice for modern DirectX 12 gaming workloads. Its 8 GB of GDDR6 memory and 288.0 GB/s bandwidth provide ample headroom for current game textures and resolutions, while its 28 ray tracing cores enable hardware-accelerated ray tracing effects that the P106-090 cannot process at all.

In Geekbench OpenCL, the RX 9060 leads by 313.9%, reflecting its massive FP32 compute advantage of 21.43 TFLOPS versus 2.352 TFLOPS. This makes the RX 9060 the superior option for general-purpose compute tasks such as rendering, scientific simulations, or machine learning inference. The FP16 capability is particularly notable: the RX 9060 handles FP16 at a 1:1 ratio, while the P106-090's 1:64 ratio means it processes FP16 at a fraction of its FP32 speed.

The Geekbench Vulkan result shows the RX 9060 ahead by 112.3%, confirming its superiority in cross-platform graphics APIs. Even in Vulkan, where the P106-090's Pascal architecture performs relatively better than in other tests, the RX 9060 still doubles its score. The RX 9060's PCIe 5.0 x16 interface ensures it can feed data to the GPU without bottleneck, whereas the P106-090's PCIe 1.0 x1 interface is a severe limitation in any modern system.

The NVIDIA P106-090 has no benchmark wins in the recorded data. However, its 75 W TDP and 250 W suggested PSU make it a lower-power option for scenarios where energy consumption is the absolute priority. Its lack of display outputs means it is strictly a compute or mining card. For users with legacy systems that cannot support modern PCIe generations or power delivery, the P106-090 might function as a low-cost compute accelerator, but its 3 GB memory capacity and 192.2 GB/s bandwidth will limit it to lighter workloads. The RX 9060 is the winner in all performance categories, and the P106-090's niche is limited to power-constrained, non-display compute tasks where its older architecture can still operate.