NVIDIA GeForce RTX 4070 Mobile vs NVIDIA GeForce RTX 4070 Ti SUPER Comparison

FAQ

Q: Which GPU is faster in overall average benchmark score?

A: The NVIDIA GeForce RTX 4070 Ti SUPER has a higher average benchmark score at 31087, compared to the RTX 4070 Mobile's 27435. The desktop card also sits at the 76th percentile among all GPUs, while the mobile part sits at the 73rd percentile.

Q: Does the mobile GPU win any benchmark against the desktop card?

A: Yes, the RTX 4070 Mobile wins the Geekbench Vulkan test with a score of 108367, versus the RTX 4070 Ti SUPER's 53683. That is a 50.5% advantage for the mobile part in that specific test.

Q: How large is the performance gap in the Passmark G3D test?

A: The RTX 4070 Ti SUPER scores 31811 in Passmark G3D, while the RTX 4070 Mobile scores 19587. The desktop card is 62.4% ahead in that test.

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

A: The RTX 4070 Ti SUPER has 672.3 GB/s of bandwidth with 16 GB of GDDR6X on a 256-bit bus. The RTX 4070 Mobile has 256.0 GB/s with 8 GB of GDDR6 on a 128-bit bus. The desktop card has more than 2.6 times the bandwidth.

Q: Are both GPUs based on the same architecture?

A: Yes, both use the Ada Lovelace architecture and are manufactured on a 5 nm process at TSMC. They also both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the TDP difference between the two cards?

A: The RTX 4070 Ti SUPER has a TDP of 285 W, while the RTX 4070 Mobile has a TDP of 115 W. The desktop card draws significantly more power, which aligns with its larger chip and higher clock speeds.

Where Each One Wins

The RTX 4070 Ti SUPER wins 8 out of 9 head-to-head benchmarks, making it the clear choice for raw compute and traditional rasterization workloads. Its wins span across every DirectX generation tested, from DirectX 9 (360 vs 223, 61.4% ahead) through DirectX 12 (119 vs 85, 40% ahead). The desktop card also dominates compute-heavy tasks, as shown in the Passmark GPU Compute test where it scores 18372 versus 8399, a massive 118.7% advantage.

The RTX 4070 Mobile's single win in Geekbench Vulkan (108367 vs 53683) is notable, but it is an outlier. In every other recorded test, the desktop card holds a substantial lead. This makes the mobile GPU viable only for scenarios where Vulkan API performance is the primary metric, which is a narrow use case.

For gaming at high resolutions or with heavy graphics settings, the RTX 4070 Ti SUPER's wins in Passmark G3D (62.4% ahead) and DirectX 11 (55.3% ahead) indicate it is the stronger option. The mobile GPU is better suited for portable systems where the 115 W TDP is a practical constraint, but the data does not show it as competitive in raw performance outside of the Vulkan test.

Architecture Differences

The two GPUs share the same Ada Lovelace architecture and 5 nm TSMC process, but they are built on different chips. The RTX 4070 Ti SUPER uses the AD103 chip with 45,900 million transistors on a 379 mm² die. The RTX 4070 Mobile uses the AD106 chip with 22,900 million transistors on a 188 mm² die. The transistor density is nearly identical, at 121.1M per mm² for the desktop chip and 121.8M per mm² for the mobile chip.

The compute resources scale accordingly. The RTX 4070 Ti SUPER has 8448 shading units, 264 TMUs, and 96 ROPs, while the RTX 4070 Mobile has 4608 shading units, 144 TMUs, and 48 ROPs. The desktop card also has 66 RT cores and 264 tensor cores, versus 36 RT cores and 144 tensor cores on the mobile part.

The memory subsystem is a major architectural split. The desktop card uses 16 GB of GDDR6X on a 256-bit bus, while the mobile card uses 8 GB of GDDR6 on a 128-bit bus. This leads to the bandwidth difference of 672.3 GB/s versus 256.0 GB/s. The clock speeds also differ significantly, with the desktop card boosting to 2610 MHz versus the mobile card's 1695 MHz.

The physical design reflects their intended use. The RTX 4070 Ti SUPER is a triple-slot card with a 16-pin power connector and a suggested PSU of 600 W. The RTX 4070 Mobile is an IGP (integrated graphics package) with no power connectors, designed to be soldered into laptops.

Specification Differences

The following table summarizes the key specification differences between the two GPUs:

| Specification | RTX 4070 Ti SUPER | RTX 4070 Mobile |

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

| Chip | AD103 | AD106 |

| Transistors | 45,900 million | 22,900 million |

| Die Size | 379 mm² | 188 mm² |

| Base Clock | 2340 MHz | 1395 MHz |

| Boost Clock | 2610 MHz | 1695 MHz |

| Memory Size | 16 GB | 8 GB |

| Memory Type | GDDR6X | GDDR6 |

| Memory Bus | 256 bit | 128 bit |

| Memory Bandwidth | 672.3 GB/s | 256.0 GB/s |

| Shading Units | 8448 | 4608 |

| TMUs | 264 | 144 |

| ROPs | 96 | 48 |

| RT Cores | 66 | 36 |

| Tensor Cores | 264 | 144 |

| Pixel Rate | 250.6 GPixel/s | 81.36 GPixel/s |

| Texture Rate | 689.0 GTexel/s | 244.1 GTexel/s |

| FP32 | 44.10 TFLOPS | 15.62 TFLOPS |

| TDP | 285 W | 115 W |

| Slot Width | Triple-slot | IGP |

| Power Connectors | 1x 16-pin | None |

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

| Release Date | 2024-01-23 | 2023-01-02 |

| Production Status | End-of-life | Active |

The desktop card has roughly double the shading units, TMUs, ROPs, RT cores, and tensor cores. Its FP32 compute of 44.10 TFLOPS is nearly triple the mobile card's 15.62 TFLOPS. The memory clock is also higher on the desktop card, with 21 Gbps effective versus 16 Gbps effective on the mobile part.

Head-to-Head Benchmarks

The largest win for the RTX 4070 Ti SUPER comes in Passmark GPU Compute, where it scores 18372 versus 8399. That is a 118.7% advantage, meaning the desktop card delivers more than twice the compute throughput of the mobile part. This aligns with the FP32 specifications, where the desktop card has 44.10 TFLOPS versus 15.62 TFLOPS.

In Passmark G3D, the desktop card scores 31811 versus 19587, a 62.4% lead. This is the most relevant test for general gaming performance, and the margin is substantial. The DirectX 9 test shows a 61.4% advantage (360 vs 223), and the DirectX 10 test shows a 56% advantage (181 vs 116). DirectX 11 follows with a 55.3% lead (278 vs 179), while DirectX 12 shows a smaller but still clear 40% lead (119 vs 85).

The Passmark G2D test, which measures 2D graphics performance, also favors the desktop card with a 60.6% advantage (1225 vs 763). The Geekbench OpenCL test shows an 82.5% lead for the desktop card (199267 vs 109197), which is another strong indicator of compute performance.

The only benchmark where the RTX 4070 Mobile wins is Geekbench Vulkan, scoring 108367 versus the desktop card's 53683. That is a 50.5% advantage for the mobile part. This is a curious result, as the desktop card wins every other test by a wide margin. It may reflect driver optimization or workload characteristics specific to the Vulkan test, but the data is clear: in this single test, the mobile GPU outperforms the desktop card.

Overall, the RTX 4070 Ti SUPER wins 8 of 9 head-to-head benchmarks. The average benchmark score difference is 31087 versus 27435, which puts the desktop card about 13.3% ahead in aggregate.

The Verdict

The data makes the choice straightforward for most users. The RTX 4070 Ti SUPER is the stronger GPU in nearly every recorded benchmark, with particularly large margins in compute (118.7% in Passmark GPU Compute) and general 3D performance (62.4% in Passmark G3D). It also has more than double the memory capacity and nearly triple the bandwidth, which makes it better suited for high-resolution textures and memory-intensive workloads.

The RTX 4070 Mobile is a different class of product. Its 115 W TDP and IGP form factor make it suitable for laptops, where power draw and physical space are constrained. The single Vulkan win is interesting but does not outweigh the consistent losses across all other tests. The mobile card also has 8 GB of memory and a 128-bit bus, which will limit performance in modern games at higher settings.

For desktop builders, the RTX 4070 Ti SUPER is the obvious pick. Its end-of-life production status means it is being phased out, but the benchmark data shows it remains a capable performer. For laptop buyers, the RTX 4070 Mobile is the only option in this comparison, and its performance is adequate for 1080p gaming, though it will not match the desktop card in demanding scenarios.

The verdict: choose the RTX 4070 Ti SUPER if you need maximum performance and have the power budget for a 285 W card. Choose the RTX 4070 Mobile only if you require a portable system and can accept the significant performance gap in exchange for the 115 W power envelope.