AMD Radeon RX 6700 XT vs NVIDIA P106-100 Comparison

The AMD Radeon RX 6700 XT and the NVIDIA P106-100 occupy very different corners of the graphics card market. The RX 6700 XT is a fully featured consumer gaming GPU from the Radeon RX 6000 series, built on the RDNA 2.0 architecture with the Navi 22 chip. The P106-100, released in 2017, is a mining-specific card based on the Pascal architecture and the GP106 chip, and it has no display outputs at all. The database records show a clear performance gap, but the nature of that gap, and the specific strengths of each card, are worth examining in detail.

Head-to-Head Benchmarks

The benchmark data contains three shared tests between these two cards, and the AMD Radeon RX 6700 XT wins all three. The most striking margin appears in the Vulkan test. The RX 6700 XT scores 93,500, while the P106-100 scores 32,897. That is a lead of 184.2% for the AMD card. In practical terms, the RX 6700 XT delivers nearly three times the Vulkan performance, which reflects the massive difference in raw compute resources and architectural efficiency.

The DirectX 12 test, recorded as 3DMark Steel Nomad, shows a similar pattern. The RX 6700 XT scores 2,435 points, versus 899 for the P106-100. The delta here is 170.9%. This is a modern, demanding workload, and the AMD card’s 12 Ultimate feature set, including dedicated ray tracing cores, gives it a decisive advantage. The P106-100, with its Pascal architecture and no ray tracing hardware, falls far behind in this scenario.

The closest contest is in the OpenCL benchmark. The RX 6700 XT scores 44,152, and the P106-100 scores 35,951. The delta is 22.8%. While still a clear win for the AMD card, this smaller gap suggests that the P106-100 is relatively more competitive in compute-heavy, driver-optimized OpenCL workloads. Its 4.375 TFLOPS of FP32 performance, while low compared to the RX 6700 XT’s 13.21 TFLOPS, still allows it to process certain parallel tasks without being completely overwhelmed.

The overall average benchmark score reinforces this hierarchy. The RX 6700 XT has an average score of 27,425, while the P106-100 averages 23,249. The database places the RX 6700 XT in the 72nd percentile of all GPUs, and the P106-100 in the 68th percentile. Despite the massive per-test gaps, the percentile difference is only four points, because the P106-100’s limited benchmark set (only three tests) is weighted differently. Still, the head-to-head results are unambiguous: the RX 6700 XT wins every shared test, with margins ranging from 22.8% to 184.2%.

Where Each One Wins

The RX 6700 XT wins in every scenario where modern gaming or graphics acceleration is required. Its 40 dedicated ray tracing cores, support for DirectX 12 Ultimate (feature level 12_2), and Vulkan 1.4 support make it suitable for current-generation titles and future software. The 3DMark Steel Nomad result, a DirectX 12 test, shows a 170.9% advantage, which means the RX 6700 XT handles complex geometry, advanced lighting, and high-resolution textures with far greater ease. Its 12 GB of GDDR6 memory on a 192-bit bus provides 384.0 GB/s of bandwidth, which feeds its 2560 shading units and 160 texture mapping units. This card is designed for sustained high-frame-rate gaming at 1440p and beyond.

The P106-100, by contrast, has no display outputs, so it cannot drive a monitor. Its only purpose is compute, and within that narrow role, it has a specific niche. The OpenCL benchmark shows that it can still deliver respectable performance in certain GPU compute tasks. Its 6 GB of GDDR5 memory on a 192-bit bus provides 192.2 GB/s of bandwidth, and its 1280 shading units and 80 texture mapping units are sufficient for workloads that do not require modern graphics features. The P106-100 also has a much lower power draw, with a TDP of 120 W versus 230 W for the RX 6700 XT, which makes it easier to install in systems with modest power supplies. The suggested PSU is 300 W for the P106-100, compared to 550 W for the RX 6700 XT.

For any task that involves rendering a frame to a screen, gaming, or using modern graphics APIs, the RX 6700 XT is the only viable option. For headless compute tasks, particularly those that use OpenCL, the P106-100 can serve as a low-power accelerator, but its 22.8% deficit in OpenCL means it is not a performance leader even in its own domain.

Architecture Differences

The architectural divide between these two cards is vast. The RX 6700 XT uses RDNA 2.0, a modern architecture from AMD, fabricated on a 7 nm process at TSMC. The chip, Navi 22, contains 17,200 million transistors on a die size of 335 mm². The transistor density is 51.3 million per square millimeter. This high-density process allows for a base clock of 2321 MHz, a game clock of 2424 MHz, and a boost clock of 2581 MHz. The memory runs at 2000 MHz, with an effective data rate of 16 Gbps. The architecture includes 40 ray tracing cores, which are absent entirely from the P106-100, and supports DirectX 12 Ultimate, Vulkan 1.4, and OpenGL 4.6.

The P106-100 uses the much older Pascal architecture, built on a 16 nm process, also at TSMC. The GP106 chip has 4,400 million transistors on a die size of 200 mm², giving a transistor density of 22.0 million per square millimeter. The base clock is 1506 MHz, and the boost clock is 1709 MHz. Memory runs at 2002 MHz, with an effective rate of 8 Gbps. Pascal does not have ray tracing cores, tensor cores, or any hardware acceleration for DirectX 12 Ultimate features. It supports DirectX 12 at feature level 12_1, Vulkan 1.4, and OpenGL 4.6, but lacks the advanced feature set of RDNA 2.0.

The FP32 compute throughput tells the story plainly. The RX 6700 XT delivers 13.21 TFLOPS, while the P106-100 delivers 4.375 TFLOPS. The FP16 performance is even more lopsided in favor of AMD, with the RX 6700 XT achieving 26.43 TFLOPS (at a 2:1 ratio), while the P106-100 manages only 68.36 GFLOPS (at a 1:64 ratio). The RX 6700 XT also has higher pixel and texture rates: 165.2 GPixel/s and 413.0 GTexel/s, versus 82.03 GPixel/s and 136.7 GTexel/s for the P106-100. The P106-100’s pixel rate is roughly half, and its texture rate is less than a third, of the AMD card’s figures.

The bus interface also differs. The RX 6700 XT uses PCIe 4.0 x16, while the P106-100 uses PCIe 1.0 x16. This older bus standard severely limits data transfer between the CPU and the GPU, which can bottleneck compute workloads. The RX 6700 XT also has a full set of display outputs (1x HDMI 2.1 and 3x DisplayPort 1.4a), while the P106-100 has no outputs, a direct consequence of its mining origin.

FAQ

Q: Which card is faster in the 3DMark Steel Nomad DirectX 12 test?

A: The AMD Radeon RX 6700 XT scores 2,435 points, while the NVIDIA P106-100 scores 899 points. The RX 6700 XT is 170.9% faster in this test.

Q: Does the NVIDIA P106-100 support ray tracing?

A: No. The P106-100 has no ray tracing cores. The AMD Radeon RX 6700 XT has 40 dedicated ray tracing cores.

Q: Can the P106-100 be used to connect a monitor?

A: No. The P106-100 has no display outputs. The RX 6700 XT includes 1x HDMI 2.1 and 3x DisplayPort 1.4a outputs.

Q: What is the memory bandwidth difference between the two cards?

A: The RX 6700 XT has 384.0 GB/s of bandwidth with 12 GB of GDDR6 memory. The P106-100 has 192.2 GB/s of bandwidth with 6 GB of GDDR5 memory.

Q: Which card has a higher average benchmark score?

A: The RX 6700 XT has an average benchmark score of 27,425, while the P106-100 has an average of 23,249.

Q: What is the process node for each card?

A: The RX 6700 XT uses a 7 nm process, and the P106-100 uses a 16 nm process. Both are fabricated by TSMC.

Specification Differences

The two cards differ in nearly every measurable specification. The RX 6700 XT uses the RDNA 2.0 architecture, while the P106-100 uses Pascal. The process node is 7 nm for AMD and 16 nm for NVIDIA. Transistor counts are 17,200 million for the RX 6700 XT and 4,400 million for the P106-100. Die sizes are 335 mm² and 200 mm², respectively.

Clock speeds are higher on the AMD card: base clock 2321 MHz versus 1506 MHz, and boost clock 2581 MHz versus 1709 MHz. The RX 6700 XT also has a game clock of 2424 MHz, which the P106-100 lacks entirely. Memory specifications differ in both type and capacity. The RX 6700 XT has 12 GB of GDDR6, while the P106-100 has 6 GB of GDDR5. The effective memory speed is 16 Gbps versus 8 Gbps.

Compute resources are significantly higher on the RX 6700 XT. It has 2560 shading units, 160 TMUs, and 64 ROPs. The P106-100 has 1280 shading units, 80 TMUs, and 48 ROPs. The RX 6700 XT also has 40 ray tracing cores; the P106-100 has none. Pixel rate is 165.2 GPixel/s versus 82.03 GPixel/s. Texture rate is 413.0 GTexel/s versus 136.7 GTexel/s. FP32 performance is 13.21 TFLOPS versus 4.375 TFLOPS. FP16 performance is 26.43 TFLOPS versus 68.36 GFLOPS.

Power requirements are lower for the P106-100, with a TDP of 120 W versus 230 W. The suggested PSU is 300 W versus 550 W. Both are dual-slot cards, but the RX 6700 XT requires a 1x 6-pin plus 1x 8-pin power connector, while the P106-100 only needs a single 6-pin connector. The bus interface is PCIe 4.0 x16 for the RX 6700 XT and PCIe 1.0 x16 for the P106-100. The RX 6700 XT has display outputs, while the P106-100 has none. DirectX support is 12 Ultimate (12_2) for AMD and 12 (12_1) for NVIDIA. The RX 6700 XT measures 267 mm in length, 110 mm in height, and 40 mm in width. The P106-100 is 250 mm long, with no recorded height or width. The RX 6700 XT was released in 2021, while the P106-100 was released in 2017. Both are end-of-life products, but the RX 6700 XT has a launch MSRP of 479 USD, while the P106-100 has no recorded launch MSRP.