NVIDIA GeForce RTX 4070 Mobile vs NVIDIA P106-100 Comparison

FAQ

Q: How much faster is the NVIDIA GeForce RTX 4070 Mobile than the NVIDIA P106-100 in OpenCL?

A: The RTX 4070 Mobile scores 109197 in Geekbench OpenCL, while the P106-100 scores 35951. That is a 203.7% advantage for the RTX 4070 Mobile.

Q: Which GPU has the higher average benchmark score?

A: The RTX 4070 Mobile has an average benchmark score of 27435, placing it in the 73rd percentile of all GPUs. The P106-100 averages 23249, placing it in the 68th percentile.

Q: What are the closest rivals to each GPU according to the database?

A: The RTX 4070 Mobile sits within 1.5% of the AMD Radeon RX 6700 XT (27425), NVIDIA GeForce RTX 3090 (27565), NVIDIA RTX PRO 4000 Blackwell (27135), and AMD Radeon Pro Vega 20 (27839). The P106-100 is nearly tied with the AMD Radeon Pro Vega 16 (23250), AMD Radeon RX 6600M (23273), AMD Radeon R9 M290X (23276), and AMD Radeon AI PRO R9700 (23315).

Q: Does the P106-100 have any benchmark win over the RTX 4070 Mobile?

A: No. In the head-to-head comparison, the RTX 4070 Mobile wins both recorded tests: Geekbench OpenCL and Geekbench Vulkan. The P106-100 has zero wins.

Q: What is the difference in transistor density between the two chips?

A: The RTX 4070 Mobile uses AD106 built on a 5 nm process with 22,900 million transistors on a 188 mm² die, yielding 121.8M transistors per mm². The P106-100 uses GP106 on a 16 nm process with 4,400 million transistors on a 200 mm² die, yielding 22.0M per mm².

Q: Which GPU supports DirectX 12 Ultimate?

A: Only the RTX 4070 Mobile supports DirectX 12 Ultimate (12_2). The P106-100 is limited to DirectX 12 (12_1).

Architecture Differences

The RTX 4070 Mobile is built on the Ada Lovelace architecture using the AD106 chip, while the P106-100 is a Pascal-generation part based on GP106. The process node gap is substantial: the RTX 4070 Mobile uses a 5 nm process from TSMC, whereas the P106-100 uses TSMC's 16 nm process. This partly explains the dramatic difference in transistor counts, 22,900 million versus 4,400 million, and the much higher transistor density of 121.8M per mm² against 22.0M per mm².

The RTX 4070 Mobile integrates 4608 shading units, 144 texture mapping units, and 48 ROPs. It also carries 36 ray tracing cores and 144 tensor cores, features entirely absent from the P106-100. The P106-100 has 1280 shading units, 80 TMUs, and 48 ROPs, matching the RTX 4070 Mobile in ROP count but falling far behind in the other compute resources.

Memory architecture also diverges sharply. The RTX 4070 Mobile uses 8 GB of GDDR6 on a 128-bit bus, delivering 256.0 GB/s of bandwidth. The P106-100 uses 6 GB of GDDR5 on a 192-bit bus, which sounds wider but only achieves 192.2 GB/s due to slower memory clocks. The memory clock figures are nearly identical (2000 MHz versus 2002 MHz), but the effective data rates differ: 16 Gbps versus 8 Gbps.

The FP16 capability reveals a generational chasm. The RTX 4070 Mobile delivers 15.62 TFLOPS of FP16 at a 1:1 ratio with FP32, meaning it treats FP16 and FP32 equally. The P106-100 offers only 68.36 GFLOPS of FP16 at a 1:64 ratio, indicating that FP16 is heavily deprioritized on Pascal. This is a fundamental architectural difference, not just a clock speed gap.

The P106-100 lacks display outputs entirely, a hallmark of its mining-focused design. It also uses a PCIe 1.0 x16 interface, while the RTX 4070 Mobile uses PCIe 4.0 x8. The RTX 4070 Mobile is an integrated GPU package (IGP slot width) with no power connectors, whereas the P106-100 is a dual-slot card requiring a 6-pin power connector and a 300 W suggested PSU.

Head-to-Head Benchmarks

The database records two direct comparisons between these GPUs, and both are decisive wins for the RTX 4070 Mobile. In Geekbench OpenCL, the RTX 4070 Mobile scores 109197 against 35951 for the P106-100, a 203.7% lead. In Geekbench Vulkan, the margin expands further: 108367 versus 32897, a 229.4% difference.

These results align with the broader compute capabilities. The RTX 4070 Mobile's FP32 throughput of 15.62 TFLOPS is over three times the P106-100's 4.375 TFLOPS. The texture fill rate tells a similar story: 244.1 GTexel/s versus 136.7 GTexel/s, a 78.5% advantage. Pixel rates are nearly identical, 81.36 GPixel/s versus 82.03 GPixel/s, which reflects the equal ROP counts.

The average benchmark score places the RTX 4070 Mobile at 27435, which is within a rounding error of the AMD Radeon RX 6700 XT (27425) and only 0.5% behind the NVIDIA GeForce RTX 3090 (27565). The P106-100's average of 23249 puts it in a completely different performance tier, matching the AMD Radeon Pro Vega 16 exactly (23250).

Notably, the P106-100 has a 3DMark Steel Nomad DX12 score of 899, a test the RTX 4070 Mobile does not appear in for this database. However, the RTX 4070 Mobile has a much richer benchmark portfolio, including Passmark scores across DirectX 9 through 12, G2D, G3D, and GPU compute. Its Passmark G3D score of 19587 and GPU compute score of 8399 indicate strong general-purpose and gaming performance.

Specification Differences

The two GPUs differ across nearly every measurable specification. The RTX 4070 Mobile uses the AD106 chip with 22,900 million transistors on a 188 mm² die, while the P106-100 uses GP106 with 4,400 million transistors on a 200 mm² die. Despite the smaller die, the RTX 4070 Mobile packs over five times the transistors.

Clock speeds are close at the boost level: the RTX 4070 Mobile boosts to 1695 MHz, the P106-100 to 1709 MHz. Base clocks differ by 111 MHz in favor of the P106-100 (1506 MHz versus 1395 MHz). But the architectural efficiency of Ada Lovelace renders those clock differences irrelevant.

Memory capacity favors the RTX 4070 Mobile at 8 GB versus 6 GB. Memory type differs: GDDR6 versus GDDR5. Bus width favors the P106-100 at 192-bit versus 128-bit, yet the RTX 4070 Mobile still achieves 33% more bandwidth (256.0 GB/s versus 192.2 GB/s) because its effective memory clock is double.

The RTX 4070 Mobile has 4608 shading units, 144 TMUs, 36 RT cores, and 144 tensor cores. The P106-100 has 1280 shading units, 80 TMUs, and no RT or tensor cores. Both have 48 ROPs. FP32 performance is 15.62 TFLOPS versus 4.375 TFLOPS. FP16 performance is 15.62 TFLOPS versus 68.36 GFLOPS.

Physical and power characteristics diverge. The RTX 4070 Mobile has a 115 W TDP, is IGP-form-factor, has no power connectors, and no display outputs of its own (portable device dependent). The P106-100 has a 120 W TDP, is dual-slot, requires one 6-pin connector, has a 300 W suggested PSU, and has no display outputs at all. The P106-100 is 250 mm long.

API support differs: the RTX 4070 Mobile supports DirectX 12 Ultimate (12_2), the P106-100 only DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4. The production status is Active for the RTX 4070 Mobile and End-of-life for the P106-100. Release dates are 2023-01-02 versus 2017-06-18.

The Verdict

The data is unambiguous. The RTX 4070 Mobile outperforms the P106-100 by more than 200% in both recorded benchmark tests. Its average benchmark score of 27435 places it in the 73rd percentile of all GPUs, while the P106-100 sits at 23249 in the 68th percentile. The RTX 4070 Mobile matches or exceeds desktop GPUs like the Radeon RX 6700 XT and comes within half a percent of the RTX 3090. The P106-100 competes with much older or lower-tier parts like the Radeon Pro Vega 16 and Radeon RX 6600M.

For anyone choosing between these two, the RTX 4070 Mobile is the clear pick for modern workloads. It has ray tracing cores, tensor cores, DirectX 12 Ultimate support, double the memory, and over three times the FP32 throughput. It is also an active product from the GeForce 40-series, whereas the P106-100 is end-of-life and was designed for mining, not general-purpose use.

The P106-100's only advantages are its wider memory bus (192-bit versus 128-bit), slightly higher boost clock (1709 MHz versus 1695 MHz), and marginally higher pixel rate (82.03 GPixel/s versus 81.36 GPixel/s). None of these translate into practical performance wins in the recorded benchmarks. The P106-100 also has a 3DMark Steel Nomad DX12 score of 899, a test not recorded for the RTX 4070 Mobile, but that single data point does not offset the massive losses elsewhere.

Where Each One Wins

The RTX 4070 Mobile wins every head-to-head benchmark recorded in the database. Its Geekbench OpenCL advantage of 203.7% and Vulkan advantage of 229.4% suggest it is overwhelmingly faster for general compute and graphics workloads. The Passmark suite further supports this: DirectX 11 score of 179, DirectX 12 score of 85, G3D score of 19587, and GPU compute score of 8399 all point to strong performance in both gaming and compute scenarios.

The RTX 4070 Mobile wins on memory bandwidth (256.0 GB/s versus 192.2 GB/s), texture fill rate (244.1 GTexel/s versus 136.7 GTexel/s), and FP32 throughput (15.62 TFLOPS versus 4.375 TFLOPS). Its 36 RT cores and 144 tensor cores give it capabilities the P106-100 simply does not have, making it suitable for ray-traced games, AI inference, and DLSS workloads.

The P106-100 wins in a few narrow specification categories. Its pixel rate is slightly higher (82.03 GPixel/s versus 81.36 GPixel/s), which is a marginal edge in fill-rate-bound scenarios. Its boost clock is 14 MHz higher. Its memory bus is 64 bits wider. But these advantages do not produce any benchmark victory.

The P106-100 also wins on physical integration in one sense: it is a standard dual-slot card with a 6-pin connector and a 300 W suggested PSU, which makes it straightforward to install in a desktop. The RTX 4070 Mobile is an IGP with no power connectors and portable-device-dependent display outputs, meaning it is tied to a laptop or mobile chassis. For a fixed desktop system, the P106-100 is easier to deploy, but for raw performance, the RTX 4070 Mobile dominates in every recorded measurement.