NVIDIA GeForce RTX 3070 Ti Mobile vs NVIDIA P106-100 Comparison

The NVIDIA GeForce RTX 3070 Ti Mobile decisively outperforms the NVIDIA P106-100 across every shared benchmark, with a commanding lead in raw compute and modern API workloads. The data shows a complete sweep: the RTX 3070 Ti Mobile wins all three head-to-head tests, with deltas ranging from 186.1% to 204.1% in its favor. While the P106-100 holds a higher percentile rank relative to all GPUs (68th versus 69th for the RTX 3070 Ti Mobile) due to its inclusion in a broader dataset, the direct comparison leaves no ambiguity about which part delivers superior performance.

Head-to-Head Benchmarks

The most significant margin appears in the Geekbench Vulkan test, where the RTX 3070 Ti Mobile scores 100,027 against the P106-100's 32,897. That is a 204.1% advantage, meaning the Ampere-based mobile GPU more than triples the Pascal mining card's output in this API. This result highlights the RTX 3070 Ti Mobile's architectural maturity, as Vulkan 1.4 support paired with 46 RT cores and 184 tensor cores allows it to handle modern rendering paths far more efficiently than the P106-100's bare Pascal design.

The Geekbench OpenCL result follows a similar pattern, with the RTX 3070 Ti Mobile posting 106,022 versus 35,951 for the P106-100, a 194.9% delta. This near-tripling of compute throughput aligns with the raw specification gap: the RTX 3070 Ti Mobile delivers 16.60 TFLOPS FP32 against 4.375 TFLOPS for the P106-100, and its 5,888 shading units dwarf the older card's 1,280. Interestingly, the FP16 comparison is even more lopsided—16.60 TFLOPS versus 68.36 GFLOPS—though the OpenCL benchmark does not isolate that metric.

The 3DMark Steel Nomad DX12 test shows the smallest relative gap, yet it is still overwhelming: 2,572 for the RTX 3070 Ti Mobile versus 899 for the P106-100, a 186.1% difference. This test stresses DirectX 12 Ultimate features, which the RTX 3070 Ti Mobile supports (12_2) while the P106-100 only reaches 12_1. The absence of ray tracing and variable-rate shading hardware on the Pascal chip explains why it falls behind even in a benchmark that does not explicitly use RT cores.

When placed against their respective nearest rivals, the two cards occupy different competitive tiers. The RTX 3070 Ti Mobile's average benchmark score of 23,518 sits within 0.9% of the AMD Radeon AI PRO R9700 (23,315) and just 0.5% below the NVIDIA GeForce RTX 3080 Mobile (23,628). In contrast, the P106-100's average of 23,249 ties with the AMD Radeon Pro Vega 16 (23,250) and trails the AMD Radeon R9 M290X by only 0.1%. This suggests that while the P106-100 is competitive within its own niche, it does not approach the performance class of the RTX 3070 Ti Mobile, which trades blows with far more modern parts.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce RTX 3070 Ti Mobile averages 23,518 points, while the NVIDIA P106-100 averages 23,249 points. This is a difference of 269 points, or roughly 1.2% in favor of the mobile Ampere part.

Q: How much faster is the RTX 3070 Ti Mobile in 3DMark Steel Nomad DX12?

A: The RTX 3070 Ti Mobile scores 2,572 versus 899 for the P106-100, making it 186.1% faster in that specific DirectX 12 test.

Q: Does the P106-100 have any benchmark where it wins?

A: No. In the three shared benchmarks—3DMark Steel Nomad DX12, Geekbench OpenCL, and Geekbench Vulkan—the RTX 3070 Ti Mobile wins all three. The P106-100 has zero head-to-head victories.

Q: What explains the P106-100's near-identical percentile ranking despite losing badly head-to-head?

A: The P106-100 sits at the 68th percentile versus the RTX 3070 Ti Mobile's 69th. This near-tie reflects the fact that the P106-100's average score of 23,249 is only 1.2% below the mobile card's 23,518, and its nearest rivals (AMD Radeon Pro Vega 16, AMD Radeon RX 6600M) are within 0.1% of its score. The head-to-head tests, however, use different workloads that expose a far larger gap.

Q: Which card has better API support?

A: The RTX 3070 Ti Mobile supports DirectX 12 Ultimate (12_2), while the P106-100 only supports DirectX 12 (12_1). Both cards support OpenGL 4.6 and Vulkan 1.4.

Q: What is the memory configuration difference?

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

The Verdict

The data is unambiguous: the NVIDIA GeForce RTX 3070 Ti Mobile is the superior GPU for any workload that requires modern graphics features or high compute throughput. Its 3-0 head-to-head sweep, with deltas between 186.1% and 204.1%, places it in a different performance class entirely. The P106-100, despite its near-identical percentile rank and average score, cannot match the RTX 3070 Ti Mobile in the three tests where both were measured.

For a user prioritizing raw compute in OpenCL or Vulkan, the RTX 3070 Ti Mobile delivers roughly three times the performance of the P106-100. Even in the closest contest—3DMark Steel Nomad DX12—the gap remains nearly 2x. The RTX 3070 Ti Mobile also brings hardware ray tracing (46 RT cores) and tensor cores (184), features entirely absent from the P106-100, which lists null for both.

The P106-100's only advantage lies in its historical context: it was designed as a mining-specific card with no display outputs, while the RTX 3070 Ti Mobile is a portable-device part whose outputs are "Portable Device Dependent." For any gaming or professional application, the RTX 3070 Ti Mobile is the only rational choice based on the benchmark evidence.

Specification Differences

The two GPUs diverge across nearly every fundamental specification. The RTX 3070 Ti Mobile uses an 8 nm Samsung process with 17,400 million transistors on a 392 mm² die, achieving a transistor density of 44.4M/mm². The P106-100 uses a 16 nm TSMC process with 4,400 million transistors on a 200 mm² die, for a density of 22.0M/mm². That is a 4x difference in transistor count and roughly a 2x difference in die size.

Clock speeds tell a different story: the P106-100 runs at a base of 1506 MHz and boost of 1709 MHz, while the RTX 3070 Ti Mobile sits at 915 MHz base and 1410 MHz boost. Despite lower clocks, the RTX 3070 Ti Mobile achieves far higher throughput due to its larger execution resources: 5,888 shading units, 184 TMUs, and 96 ROPs, versus 1,280 shading units, 80 TMUs, and 48 ROPs for the P106-100.

Memory differs in capacity, type, and bandwidth: the RTX 3070 Ti Mobile offers 8 GB GDDR6 on a 256-bit bus with 448.0 GB/s, while the P106-100 has 6 GB GDDR5 on a 192-bit bus with 192.2 GB/s. The RTX 3070 Ti Mobile also supports PCIe 4.0 x16, whereas the P106-100 is limited to PCIe 1.0 x16. Power draw is similar—115 W for the mobile card versus 120 W for the mining card—but the P106-100 requires a 1x 6-pin connector and a 300 W PSU, while the RTX 3070 Ti Mobile uses no power connectors. The P106-100 is dual-slot and 250 mm long; the RTX 3070 Ti Mobile has no listed dimensions.

Architecture Differences

The architectural gap is generation-defining. The RTX 3070 Ti Mobile is built on Ampere, NVIDIA's modern gaming architecture, while the P106-100 uses the older Pascal architecture. Ampere brings dedicated ray tracing cores (46) and tensor cores (184), which Pascal lacks entirely—both fields are null for the P106-100. This enables hardware-accelerated ray tracing and AI-based features like DLSS on the RTX 3070 Ti Mobile, none of which are possible on the P106-100.

The FP16 compute ratio highlights another architectural split: the RTX 3070 Ti Mobile achieves FP16 at 1:1 with FP32 (16.60 TFLOPS both), while the P106-100's FP16 is 1:64 at just 68.36 GFLOPS. This means the Ampere card is fully capable of mixed-precision workloads, whereas the Pascal card is heavily optimized for FP32-only compute, reflecting its mining origins.

Process node and foundry differ: Samsung 8 nm for the RTX 3070 Ti Mobile versus TSMC 16 nm for the P106-100. The smaller node enables nearly 4x the transistor density, which translates into the massive shading unit advantage. The RTX 3070 Ti Mobile's DirectX 12 Ultimate (12_2) support versus the P106-100's DirectX 12 (12_1) further underscores the architectural leap, as 12_2 adds mesh shaders, sampler feedback, and other next-gen features absent from Pascal.

Where Each One Wins

The RTX 3070 Ti Mobile wins every measurable contest. In raw compute, it is 194.9% ahead in Geekbench OpenCL and 204.1% ahead in Geekbench Vulkan. For DirectX 12 gaming workloads, it leads by 186.1% in 3DMark Steel Nomad. The card also wins on memory bandwidth (448.0 GB/s versus 192.2 GB/s), memory capacity (8 GB versus 6 GB), and API feature support (12_2 versus 12_1).

The P106-100 has no benchmark wins, but it does hold advantages in two non-performance areas: clock speed (1709 MHz boost versus 1410 MHz) and physical design (dual-slot, 250 mm length, and a 6-pin power connector). It also has a lower transistor count and die size, which historically might correlate with lower manufacturing cost, but no pricing data is available to confirm that. The P106-100's PCIe 1.0 x16 interface is a severe bottleneck for any modern workload, while the RTX 3070 Ti Mobile's PCIe 4.0 x16 ensures full bandwidth.

For a user selecting between these two, the choice is clear. The RTX 3070 Ti Mobile is the only option for gaming, ray tracing, or general-purpose compute. The P106-100, with no display outputs and a mining-specific design, is limited to headless compute tasks—and even there, it delivers roughly one-third the performance of the RTX 3070 Ti Mobile in OpenCL. The data leaves no scenario where the P106-100 is the better pick, except perhaps for applications that require a dual-slot, 250 mm card with a 6-pin connector, where the RTX 3070 Ti Mobile's form factor is undefined.