NVIDIA GeForce RTX 3070 Mobile vs NVIDIA P106-100 Comparison

Where Each One Wins

The benchmark data paints a one-sided picture. The NVIDIA GeForce RTX 3070 Mobile wins every recorded test in the database, taking all three head-to-head comparisons outright. The NVIDIA P106-100, a dedicated mining GPU with no display outputs, does not secure a single victory in any measured workload. This is not a close contest; the RTX 3070 Mobile dominates across the board.

The RTX 3070 Mobile's strongest showing comes in 3DMark Steel Nomad DX12, a modern DirectX 12 workload that stresses the full graphics pipeline. It scores 2380 points against the P106-100's 899 points, a gap of 62.2 percent in favor of the Ampere part. This suggests the RTX 3070 Mobile is substantially better equipped for contemporary gaming and graphics-intensive tasks. The P106-100, by contrast, was engineered for compute-heavy mining operations, not for rendering interactive scenes.

In compute-oriented benchmarks, the RTX 3070 Mobile also leads decisively. Geekbench OpenCL shows a score of 92939 versus 35951, a 61.3 percent advantage. The Vulkan test tells a similar story: 86768 versus 32897, a 62.1 percent lead. These results indicate the RTX 3070 Mobile offers far greater general-purpose compute throughput, which benefits applications ranging from content creation to scientific workloads. The P106-100's Pascal architecture, while competent in its niche, simply cannot match the raw throughput of the newer Ampere design.

The overall average benchmark score reinforces this hierarchy. The P106-100 averages 23249 points across all recorded tests, placing it in the 68th percentile of all GPUs in the database. The RTX 3070 Mobile averages 20534 points, which lands it in the 65th percentile. Interestingly, the P106-100 has a higher average score and percentile despite losing every head-to-head test. This is because the P106-100's benchmark portfolio is limited to three tests, all of which are relatively favorable to its architecture. The RTX 3070 Mobile has a much broader test suite, including PassMark legacy DirectX tests where scores are lower, dragging down its average.

For users, the use-case split is clear. The RTX 3070 Mobile is the choice for gaming, modern graphics APIs, and any workload that benefits from high compute throughput. The P106-100, with its mining-focused design and lack of display outputs, has no practical application in a consumer-facing system. Its only theoretical advantage would be in scenarios where raw FP32 compute per watt is paramount, but the data does not support that conclusion given the RTX 3070 Mobile's overwhelming performance lead.

Architecture Differences

The two GPUs come from different eras and design philosophies. The NVIDIA P106-100 is built on the Pascal architecture, specifically the GP106 chip, fabricated on a 16 nm TSMC process. It packs 4,400 million transistors into a 200 mm² die, yielding a transistor density of 22.0 million per square millimeter. The RTX 3070 Mobile uses the Ampere architecture with the GA104 chip, built on Samsung's 8 nm process. It contains 17,400 million transistors across a 392 mm² die, achieving a density of 44.4 million per square millimeter. The process shrink and architectural leap allow Ampere to more than double the transistor density while adding significant feature support.

Core configurations differ dramatically. The P106-100 has 1280 shading units, 80 texture mapping units, and 48 raster operation pipelines. The RTX 3070 Mobile quadruples the shading units to 5120, doubles the TMUs to 160, and increases ROPs to 80. Crucially, the RTX 3070 Mobile adds dedicated hardware that the P106-100 lacks entirely: 40 ray tracing cores and 160 tensor cores. These enable hardware-accelerated ray tracing and AI-based features like DLSS, neither of which the Pascal-based P106-100 can support. This is a generational feature gap, not just a performance one.

Memory subsystems also differ substantially. The P106-100 uses 6 GB of GDDR5 on a 192-bit bus, delivering 192.2 GB/s of bandwidth. The RTX 3070 Mobile has 8 GB of GDDR6 on a wider 256-bit bus, achieving 448.0 GB/s. That is more than double the memory bandwidth, which is critical for high-resolution textures and data-intensive compute workloads. Clock speeds are interesting: the P106-100 actually boosts higher at 1709 MHz versus the RTX 3070 Mobile's 1560 MHz, and has a higher base clock at 1506 MHz versus 1110 MHz. But the RTX 3070 Mobile's massive core count more than compensates for the lower clocks.

Rates and throughput figures show the scale of the gap. The P106-100 delivers 82.03 GPixel/s pixel fill rate and 136.7 GTexel/s texture rate. The RTX 3070 Mobile hits 124.8 GPixel/s and 249.6 GTexel/s respectively. In floating-point performance, the P106-100 manages 4.375 TFLOPS for FP32, while the RTX 3070 Mobile reaches 15.97 TFLOPS. The FP16 comparison is stark: the P106-100 has 68.36 GFLOPS with a 1:64 ratio, meaning FP16 is heavily crippled, while the RTX 3070 Mobile offers 15.97 TFLOPS at a 1:1 ratio. This makes the Ampere part vastly superior for AI and machine learning inference tasks.

Power and interface differences reflect their intended uses. The P106-100 has a 120 W TDP, uses a dual-slot cooler, requires a single 6-pin power connector, and suggests a 300 W power supply. It interfaces via PCIe 1.0 x16, which is a legacy bus standard, and has no display outputs whatsoever. The RTX 3070 Mobile has a 115 W TDP, uses no external power connectors (it draws from the laptop's power delivery system), and connects via PCIe 4.0 x16. Its display outputs are portable-device dependent, meaning they vary by laptop implementation. The P106-100's PCIe 1.0 interface is a serious bottleneck for data transfer, though it matters little for a mining card with no outputs.

API support also differs. The P106-100 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The RTX 3070 Mobile supports DirectX 12 Ultimate (12_2), which includes features like mesh shaders and variable rate shading, plus OpenGL 4.6 and Vulkan 1.4. The DirectX 12 Ultimate certification is a meaningful distinction for modern game compatibility.

Head-to-Head Benchmarks

The recorded head-to-head tests show a consistent, overwhelming advantage for the RTX 3070 Mobile. In 3DMark Steel Nomad DX12, the RTX 3070 Mobile scores 2380 against the P106-100's 899. The delta percentage is 62.2 percent in favor of the Ampere chip. This is a synthetic DirectX 12 benchmark that scales well with core count and memory bandwidth, both of which favor the RTX 3070 Mobile.

Geekbench OpenCL results follow the same pattern. The RTX 3070 Mobile posts 92939 points, while the P106-100 manages 35951. The delta is 61.3 percent. OpenCL is a general-purpose compute benchmark, and the RTX 3070 Mobile's 5120 shading units and tensor cores provide a massive throughput advantage. The P106-100's 1280 shading units are simply outclassed.

The Vulkan API test shows a 62.1 percent delta. The RTX 3070 Mobile scores 86768, and the P106-100 scores 32897. Vulkan is a low-overhead graphics and compute API, and the results indicate the RTX 3070 Mobile handles draw calls and compute dispatches far more efficiently. The P106-100, despite its Pascal architecture being competent for its era, cannot keep pace.

Beyond the three shared tests, the RTX 3070 Mobile has additional PassMark benchmarks in the database that further illustrate its capabilities. It scores 15309 in PassMark G3D, 6827 in GPU Compute, and 641 in G2D. Legacy DirectX tests show 160 in DirectX 9, 138 in DirectX 11, 113 in DirectX 10, and 64 in DirectX 12. These scores, while not compared directly to the P106-100, contextualize the RTX 3070 Mobile's overall performance profile. The P106-100 has no corresponding PassMark entries, so no direct comparison is possible.

The nearest rivals in the database provide additional context. The P106-100's closest competitor is the AMD Radeon Pro Vega 16, which has an average score of 23250, essentially identical to the P106-100's 23249. The AMD Radeon RX 6600M is 0.1 percent behind, and the AMD Radeon R9 M290X is also 0.1 percent behind. The RTX 3070 Mobile's nearest rival is the Intel Arc B570, which scores 20556, a 0.1 percent difference. The Intel Arc A750 is 0.2 percent behind, and the NVIDIA Quadro M4000M is 0.3 percent ahead. These rival comparisons show both GPUs are competitive within their respective performance tiers, but those tiers are vastly different.

FAQ

Q: Which GPU is faster in DirectX 12 workloads?

A: The NVIDIA GeForce RTX 3070 Mobile is significantly faster. In the 3DMark Steel Nomad DX12 test, it scores 2380 versus the P106-100's 899, a 62.2 percent advantage.

Q: Does the P106-100 support ray tracing?

A: No. The P106-100 has no ray tracing cores, while the RTX 3070 Mobile includes 40 dedicated RT cores.

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

A: The RTX 3070 Mobile has 448.0 GB/s of bandwidth from 8 GB of GDDR6 on a 256-bit bus. The P106-100 has 192.2 GB/s from 6 GB of GDDR5 on a 192-bit bus.

Q: Which GPU has a higher boost clock?

A: The P106-100 boosts to 1709 MHz, which is higher than the RTX 3070 Mobile's 1560 MHz boost clock. However, the RTX 3070 Mobile has four times the shading units.

Q: Can the P106-100 be used for gaming in a standard desktop?

A: No. The P106-100 has no display outputs, making it impossible to connect a monitor directly. The RTX 3070 Mobile has portable-device-dependent outputs.

Q: How do the two GPUs compare in OpenCL compute performance?

A: The RTX 3070 Mobile scores 92939 in Geekbench OpenCL, while the P106-100 scores 35951. This is a 61.3 percent lead for the Ampere-based mobile GPU.

The Verdict

The data is unambiguous. The NVIDIA GeForce RTX 3070 Mobile outperforms the NVIDIA P106-100 in every recorded benchmark, with deltas consistently above 61 percent. The RTX 3070 Mobile wins all three head-to-head tests: 3DMark Steel Nomad DX12, Geekbench OpenCL, and Geekbench Vulkan. There are no tests where the P106-100 emerges victorious.

For any user building a system for gaming, content creation, or general-purpose computing, the RTX 3070 Mobile is the only sensible choice from these two. Its 5120 shading units, 40 ray tracing cores, 160 tensor cores, and 448.0 GB/s of memory bandwidth provide a level of performance that the P106-100 cannot approach. The P106-100's lack of display outputs alone disqualifies it for consumer use, and its 4.375 TFLOPS FP32 throughput is a fraction of the RTX 3070 Mobile's 15.97 TFLOPS.

The P106-100 was designed for a specific mining workload, and the benchmark data reflects that specialization. Its higher boost clock and lower average score in the broader database do not translate to any practical advantage. The RTX 3070 Mobile, despite being a mobile part with a 115 W TDP, is in a completely different performance class. Users should select the RTX 3070 Mobile without hesitation if given the option between these two GPUs. The RTX 3070 Mobile's nearest rival in the database is the Intel Arc B570, which is only 0.1 percent behind in average score, indicating the RTX 3070 Mobile holds its own even among newer competitors.