AMD Radeon RX 6700M vs NVIDIA P106-100 Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive sweep for the AMD Radeon RX 6700M across all three shared benchmark tests. In the 3DMark Steel Nomad DX12 test, the RX 6700M scored 1845 against the NVIDIA P106-100's 899, a 105.2% advantage. This is not a marginal lead; the AMD part more than doubles the NVIDIA card's output in this modern DirectX 12 workload.

The Geekbench results amplify the gap further. In the OpenCL test, the RX 6700M posted 77,666 versus 35,951 for the P106-100, a 116% delta. The Vulkan test is even more lopsided: 90,816 versus 32,897, which translates to a 176.1% lead for the AMD mobile GPU. The data indicates that the RX 6700M's architectural advantages scale aggressively in compute-heavy and API-modern workloads, while the P106-100 struggles to keep pace.

Looking at the overall average benchmark scores, the RX 6700M sits at 25,633, while the P106-100 averages 23,249. The RX 6700M's nearest rivals in the database include the AMD Radeon Pro W5700 at 25,726 (0.4% ahead) and the NVIDIA GeForce RTX 3080 Ti Mobile at 25,740 (0.4% ahead). The P106-100, by contrast, is essentially tied with the AMD Radeon Pro Vega 16 (23,250, 0% delta) and slightly behind the AMD Radeon RX 6600M (23,273, a 0.1% deficit). This contextual data shows that while the RX 6700M is competitive with higher-tier mobile parts, the P106-100 sits in a lower performance tier, just below the RX 6600M.

The percentile ranking reinforces this separation. The RX 6700M sits in the 71st percentile of all GPUs in the database, while the P106-100 sits in the 68th percentile. A three-point percentile gap might sound modest, but the raw score differences in individual tests tell a story of generational and architectural divergence. The RX 6700M wins all three head-to-head tests, with zero wins for the NVIDIA part.

FAQ

Q: Which GPU has the higher raw compute throughput in FP32 operations?

A: The AMD Radeon RX 6700M delivers 11.06 TFLOPS of FP32 performance, while the NVIDIA P106-100 manages 4.375 TFLOPS. The RX 6700M is roughly 2.5 times faster in this metric.

Q: How do the two cards compare in ray tracing capabilities?

A: The AMD Radeon RX 6700M includes 36 dedicated ray accelerator cores as part of its RDNA 2.0 architecture. The NVIDIA P106-100 has no ray tracing cores listed in its specification, confirming it lacks hardware-accelerated ray tracing support.

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

A: The RX 6700M features 10 GB of GDDR6 memory on a 160-bit bus, yielding 320.0 GB/s of bandwidth. The P106-100 has 6 GB of GDDR5 memory on a 192-bit bus, providing 192.2 GB/s of bandwidth. Despite the narrower bus, the AMD card's faster memory type gives it substantially more bandwidth.

Q: Which card has better API support for modern graphics features?

A: The RX 6700M supports DirectX 12 Ultimate (12_2), which includes features like DirectX Raytracing and variable rate shading. The P106-100 only supports DirectX 12 (12_1). Both cards support OpenGL 4.6 and Vulkan 1.4.

Q: How does the power draw compare between the two?

A: The RX 6700M has a TDP of 135 W, while the P106-100 has a TDP of 120 W. The AMD card draws 15 W more, but it delivers significantly higher performance per watt given its massive benchmark leads.

Q: What are the physical form factor differences?

A: The RX 6700M is an integrated graphics processor (IGP) with no dedicated slot width or power connectors, designed for portable devices. The P106-100 is a dual-slot card measuring 250 mm (9.8 inches) in length, requiring a single 6-pin power connector and a 300 W suggested power supply.

Architecture Differences

The architectural divide between these two GPUs is stark and explains much of the benchmark gap. The AMD Radeon RX 6700M is built on the RDNA 2.0 architecture using the Navi 22 chip, fabricated on a 7 nm TSMC process. The NVIDIA P106-100 uses the older Pascal architecture with the GP106 chip, manufactured on a 16 nm TSMC process. This process node difference alone accounts for significant efficiency and density gains for the AMD part.

Transistor counts highlight the scale difference. The RX 6700M packs 17,200 million transistors on a 335 mm² die, achieving a transistor density of 51.3 million per square millimeter. The P106-100 has just 4,400 million transistors on a 200 mm² die, with a density of 22.0 million per square millimeter. The AMD chip is not only larger but also more than twice as dense, reflecting the newer manufacturing process.

The execution resources differ dramatically. The RX 6700M contains 2,304 shading units, 144 texture mapping units, and 64 render output units. It also includes 36 ray tracing cores, a feature entirely absent from the Pascal-based P106-100, which has 1,280 shading units, 80 TMUs, and 48 ROPs. The AMD card also supports FP16 compute at a 2:1 ratio relative to FP32, delivering 22.12 TFLOPS of FP16 performance. The P106-100's FP16 throughput is a paltry 68.36 GFLOPS at a 1:64 ratio, indicating it was never designed for mixed-precision workloads.

The memory architecture reflects different design priorities. The RX 6700M uses a 160-bit bus with GDDR6 memory at 16 Gbps effective speed, achieving 320.0 GB/s. The P106-100 uses a wider 192-bit bus but with slower GDDR5 memory at 8 Gbps effective, capping bandwidth at 192.2 GB/s. The AMD part's higher bandwidth is crucial for its superior texture and pixel rates: 345.6 GTexel/s and 153.6 GPixel/s, respectively, versus the NVIDIA card's 136.7 GTexel/s and 82.03 GPixel/s.

The P106-100 is labeled as part of the "Mining GPUs" generation, which explains its lack of display outputs. It has no video outputs at all, making it unsuitable for standard desktop use without a secondary graphics solution. The RX 6700M, conversely, has display outputs described as "portable device dependent," meaning it relies on the laptop or mobile chassis for connectivity. The P106-100 also uses a PCIe 1.0 x16 interface, while the RX 6700M uses PCIe 4.0 x16, a substantial difference in host bandwidth.

Specification Differences

The two cards diverge on nearly every measurable specification. The RX 6700M is a mobile IGP from the Radeon RX 6000 series, released on May 30, 2021. The P106-100 is a mining-focused card released on June 18, 2017. Both are end-of-life products, but they come from different eras of GPU design.

Clock speeds favor the AMD card significantly. The RX 6700M has a base clock of 1489 MHz, a game clock of 2300 MHz, and a boost clock of 2400 MHz. The P106-100 has a base clock of 1506 MHz and a boost clock of 1709 MHz. While the NVIDIA card starts slightly higher at base, the AMD card's boost clock is nearly 700 MHz higher, contributing to its raw performance advantage.

Memory specifications differ in capacity, type, and bandwidth as detailed above. The RX 6700M's 10 GB GDDR6 configuration offers 320.0 GB/s, while the P106-100's 6 GB GDDR5 offers 192.2 GB/s. The bus widths also differ: 160-bit for AMD versus 192-bit for NVIDIA.

Power and physical requirements are distinct. The RX 6700M is an IGP with no power connectors and a 135 W TDP. The P106-100 is a dual-slot card with a single 6-pin power connector, a 120 W TDP, and a suggested power supply of 300 W. The NVIDIA card measures 250 mm in length, while the AMD mobile part has no listed dimensions since it is integrated into a portable device.

The API support differs in DirectX version: the RX 6700M supports DirectX 12 Ultimate (12_2), while the P106-100 supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4. The transistor density, die size, and process node differences are also specification-level distinctions that separate these parts.

The Verdict

The data is unambiguous: the AMD Radeon RX 6700M is the superior performer in every recorded benchmark. It wins all three head-to-head tests by margins ranging from 105.2% to 176.1%. Its average benchmark score of 25,633 places it in the 71st percentile of all GPUs, while the P106-100's 23,249 average sits in the 68th percentile.

For users considering the RX 6700M, the data shows a part that competes with the AMD Radeon Pro W5700 (0.4% ahead) and the NVIDIA GeForce RTX 3080 Ti Mobile (0.4% ahead) in average scores. It offers modern features like ray tracing cores, DirectX 12 Ultimate support, and a 7 nm process with high transistor density. It is a mobile part, so it is best suited for laptop or portable device integration where its 135 W TDP can be managed.

The P106-100, based on the recorded figures, is a mining-focused card with no display outputs. Its Pascal architecture lacks ray tracing and has minimal FP16 capability. Its average score is essentially tied with the AMD Radeon Pro Vega 16 (0% delta) and slightly behind the AMD Radeon RX 6600M (0.1% deficit). It is a dual-slot card requiring external power, making it a less flexible option for most users.

The verdict from the benchmark database is clear: choose the RX 6700M for any workload requiring modern graphics features, high compute throughput, or broad API support. The P106-100's only potential advantage is its lower 120 W TDP, but the performance gap is so large that this efficiency benefit is negligible in practice. The RX 6700M dominates across the board, and the data provides no scenario where the P106-100 emerges as the preferable option.