AMD Radeon RX 6700S vs NVIDIA P106-100 Comparison

The benchmark data clearly establishes the AMD Radeon RX 6700S as the dominant performer, decisively winning all three head-to-head tests against the NVIDIA P106-100. While the P106-100 holds a marginal edge in overall market percentile ranking, the RX 6700S delivers superior raw performance across every measurable metric, making it the unequivocal choice for compute-intensive tasks.

Head-to-Head Benchmarks

The most significant gap emerges in the Vulkan API test, where the AMD Radeon RX 6700S scores 76,150 compared to the NVIDIA P106-100's 32,897. This represents a 56.8% advantage for the AMD part, the largest delta across all comparisons. The RX 6700S's modern RDNA 2.0 architecture clearly translates into substantially better Vulkan performance, a critical factor for contemporary gaming and compute workloads.

In the OpenCL test, the RX 6700S again demonstrates overwhelming superiority, posting 70,965 points versus 35,951 for the P106-100. The 49.3% deficit for the NVIDIA card highlights a fundamental generational gap in compute throughput. This result is particularly telling given that the P106-100 was designed specifically for mining workloads, yet still falls far behind in general-purpose compute benchmarks.

The 3DMark Steel Nomad DX12 test shows the closest relative competition, though the RX 6700S still wins decisively. AMD's card scores 1,451 compared to 899 for the P106-100, a 38% difference. While this is the smallest margin of the three tests, it remains a commanding victory and underscores the RX 6700S's superior DirectX 12 capabilities.

Interestingly, the average benchmark scores tell a slightly different story. The P106-100 achieves an average score of 23,249 across all its benchmarks, placing it in the 68th percentile of all GPUs. The RX 6700S averages 22,154, ranking in the 67th percentile. This near-parity in overall averages is misleading, however, as it reflects different benchmark suites rather than true performance equivalence. The head-to-head results are unambiguous: the RX 6700S wins every single direct comparison.

Architecture Differences

The architectural chasm between these two GPUs explains their performance disparity. The NVIDIA P106-100 utilizes the GP106 chip built on the Pascal architecture, manufactured on TSMC's 16 nm process. It contains 4,400 million transistors on a 200 mm² die, yielding a transistor density of 22.0 million per mm². In contrast, the AMD Radeon RX 6700S employs the Navi 23 chip with RDNA 2.0 architecture, fabricated on a 7 nm process. This newer node allows AMD to pack 11,060 million transistors into a 237 mm² die, achieving a density of 46.7 million per mm² — more than double the P106-100's density.

The memory subsystems diverge significantly. The P106-100 offers 6 GB of GDDR5 memory on a 192-bit bus, delivering 192.2 GB/s of bandwidth. The RX 6700S provides 8 GB of GDDR6 memory on a narrower 128-bit bus, yet achieves higher bandwidth at 224.0 GB/s thanks to faster memory technology. This bandwidth advantage proves crucial in memory-intensive workloads.

Compute resources also favor the AMD card substantially. The RX 6700S houses 1,792 shading units, 112 texture mapping units, and 64 ROPs. The P106-100 counters with 1,280 shading units, 80 TMUs, and 48 ROPs. The AMD card additionally features 28 ray tracing cores, a capability entirely absent from the NVIDIA part. The RX 6700S outputs 128.0 GPixel/s and 224.0 GTexel/s, while the P106-100 manages 82.03 GPixel/s and 136.7 GTexel/s.

Clock speeds reinforce AMD's advantage. The RX 6700S runs at a 1700 MHz base clock and 2000 MHz boost, with a game clock of 1890 MHz. The P106-100 operates at 1506 MHz base and 1709 MHz boost. Floating-point performance reflects this: the RX 6700S delivers 7.168 TFLOPS FP32, while the P106-100 achieves 4.375 TFLOPS. The FP16 comparison is even more stark, with the RX 6700S producing 14.34 TFLOPS versus a meager 68.36 GFLOPS for the NVIDIA card, which uses a severely limited 1:64 ratio.

The power profiles present an interesting contrast. The P106-100 carries a 120 W TDP and requires a 1x 6-pin power connector with a 300 W suggested PSU. The RX 6700S, despite delivering far higher performance, consumes only 80 W TDP and requires no external power connectors, operating as an IGP with portable-device-dependent display outputs. This efficiency stems directly from the advanced 7 nm process node.

FAQ

Q: Which GPU has higher raw compute performance?

A: The AMD Radeon RX 6700S delivers 7.168 TFLOPS FP32 compared to the NVIDIA P106-100's 4.375 TFLOPS, representing a substantial 63.8% advantage for AMD.

Q: How do their memory bandwidth figures compare?

A: The RX 6700S provides 224.0 GB/s bandwidth from 8 GB of GDDR6 on a 128-bit bus, while the P106-100 offers 192.2 GB/s from 6 GB of GDDR5 on a 192-bit bus.

Q: What is the power consumption difference?

A: The RX 6700S draws only 80 W TDP with no external power connectors, whereas the P106-100 consumes 120 W and requires a 1x 6-pin connector with a 300 W suggested PSU.

Q: Which GPU supports ray tracing?

A: Only the AMD Radeon RX 6700S features 28 ray tracing cores; the NVIDIA P106-100 has no ray tracing hardware at all.

Q: How do their DirectX support levels differ?

A: The RX 6700S supports DirectX 12 Ultimate (12_2), while the P106-100 only reaches DirectX 12 (12_1).

Q: What are their respective production statuses?

A: Both GPUs are end-of-life. The P106-100 was released in 2017, while the RX 6700S launched in 2022.

The Verdict

The data leaves no room for ambiguity: the AMD Radeon RX 6700S is the superior GPU in every head-to-head benchmark. Its 38% advantage in 3DMark Steel Nomad, 49.3% lead in OpenCL, and 56.8% margin in Vulkan establish it as the clear performance winner. The architectural advantages — newer 7 nm process, more transistors, ray tracing support, higher clock speeds, and doubled FP16 throughput — all translate directly into benchmark victories.

The P106-100's only statistical claim is its marginally higher average benchmark score (23,249 vs 22,154) and 68th percentile ranking compared to AMD's 67th. However, these figures reflect different benchmark compositions rather than genuine performance superiority. In direct competition, the NVIDIA card loses every test.

For anyone choosing between these two based purely on the available data, the RX 6700S is the obvious selection. It wins on performance, efficiency, memory capacity, bandwidth, and modern feature support. The P106-100, being a mining-specific GPU with no display outputs, simply cannot compete with a purpose-built mobile gaming GPU from a later generation.

Specification Differences

| Specification | NVIDIA P106-100 | AMD Radeon RX 6700S |

|---|---|---|

| Process Node | 16 nm | 7 nm |

| Transistors | 4,400 million | 11,060 million |

| Die Size | 200 mm² | 237 mm² |

| Transistor Density | 22.0M / mm² | 46.7M / mm² |

| Base Clock | 1506 MHz | 1700 MHz |

| Boost Clock | 1709 MHz | 2000 MHz |

| Memory Size | 6 GB | 8 GB |

| Memory Type | GDDR5 | GDDR6 |

| Memory Bus | 192 bit | 128 bit |

| Memory Bandwidth | 192.2 GB/s | 224.0 GB/s |

| Shading Units | 1280 | 1792 |

| TMUs | 80 | 112 |

| ROPs | 48 | 64 |

| Ray Tracing Cores | None | 28 |

| Pixel Rate | 82.03 GPixel/s | 128.0 GPixel/s |

| Texture Rate | 136.7 GTexel/s | 224.0 GTexel/s |

| FP32 Performance | 4.375 TFLOPS | 7.168 TFLOPS |

| FP16 Performance | 68.36 GFLOPS | 14.34 TFLOPS |

| TDP | 120 W | 80 W |

| Power Connectors | 1x 6-pin | None |

| Suggested PSU | 300 W | None |

| Bus Interface | PCIe 1.0 x16 | PCIe 4.0 x8 |

| Display Outputs | No outputs | Portable Device Dependent |

| DirectX Support | 12 (12_1) | 12 Ultimate (12_2) |

| Release Date | 2017 | 2022 |

Where Each One Wins

The AMD Radeon RX 6700S wins in every measurable performance category. Its advantages in Vulkan and OpenCL make it the superior choice for compute-heavy applications, while its 3DMark Steel Nomad victory demonstrates stronger DirectX 12 gaming potential. The 28 ray tracing cores provide future-proofing for ray-traced content, a feature completely unavailable on the NVIDIA card. Higher memory bandwidth (224.0 GB/s vs 192.2 GB/s) ensures better performance in memory-bound scenarios, and the larger 8 GB frame buffer allows for higher resolution textures and more demanding workloads.

The NVIDIA P106-100's advantages are limited to non-performance areas. Its average benchmark score of 23,249 slightly exceeds the RX 6700S's 22,154, and its 68th percentile ranking edges out AMD's 67th. The dual-slot form factor and 250 mm length suggest a traditional desktop installation profile, whereas the RX 6700S's IGP form factor targets mobile platforms. The P106-100's 6 GB memory on a wider 192-bit bus might offer better latency characteristics in specific narrow workloads, though the benchmark data does not support this conclusion.

In practical terms, the RX 6700S wins for gaming, compute, ray tracing, and energy-efficient performance. The P106-100 wins only for those requiring a mining-specific GPU with no display output, though its benchmark results suggest even that use case is poorly served compared to the newer AMD part. The choice is clear: the AMD Radeon RX 6700S is the better GPU by every available performance metric.