NVIDIA GeForce RTX 4070 SUPER vs NVIDIA GeForce RTX 4090 Mobile Comparison

# The Verdict

The benchmark data presents a fascinating inversion of expectations. Despite carrying the higher-tier "4090" name, the NVIDIA GeForce RTX 4090 Mobile and the NVIDIA GeForce RTX 4070 SUPER are remarkably close in overall performance, with the desktop card edging ahead in the majority of tests. The RTX 4070 SUPER wins 7 of the 9 head-to-head comparisons, while the RTX 4090 Mobile manages only 2 victories. The average benchmark scores tell the story: the RTX 4090 Mobile posts 43667, while the RTX 4070 SUPER trails only slightly at 43223, a difference of just 1%. Both cards sit in the same performance tier, with the RTX 4090 Mobile at the 84th percentile of all GPUs and the RTX 4070 SUPER at the 83rd.

For users prioritizing raw graphics throughput, the RTX 4070 SUPER is the clear choice. Its Passmark G3D score of 29995 beats the mobile card's 27212 by 9.3%, and its Passmark GPU compute score of 17108 crushes the RTX 4090 Mobile's 12347 by a massive 27.8%. The desktop card also wins in DirectX 9, 11, and 12 legacy tests, plus 2D performance. However, the RTX 4090 Mobile holds advantages in OpenCL workloads (180831 vs 172795, a 4.7% lead) and DirectX 10 (173 vs 167, a 3.6% lead). The RTX 4070 SUPER is the pick for gaming and compute-heavy tasks, while the RTX 4090 Mobile is better suited for specific OpenCL-accelerated applications. The RTX 4070 SUPER's launch MSRP is 599 USD.

Architecture Differences

Both GPUs are built on the Ada Lovelace architecture and manufactured on TSMC's 5 nm process node, but they use different chips. The RTX 4090 Mobile is powered by the AD103 chip, which contains 45,900 million transistors on a 379 mm² die. The RTX 4070 SUPER uses the smaller AD104 chip, packing 35,800 million transistors into a 294 mm² die. Transistor density is nearly identical: 121.1M per mm² for the mobile chip versus 121.8M per mm² for the desktop chip.

The RTX 4090 Mobile has a substantially larger compute configuration. It features 9728 shading units, 304 texture mapping units, and 112 render output units. The RTX 4070 SUPER is cut down significantly, with 7168 shading units, 224 TMUs, and 80 ROPs. Ray tracing hardware follows the same pattern: 76 RT cores on the mobile card versus 56 on the desktop card. Tensor cores also differ, with 304 on the RTX 4090 Mobile and 224 on the RTX 4070 SUPER.

Memory configurations are distinct. The RTX 4090 Mobile pairs its 16 GB of GDDR6 memory with a 256-bit bus, delivering 576.0 GB/s of bandwidth. The RTX 4070 SUPER uses 12 GB of faster GDDR6X memory on a narrower 192-bit bus, resulting in 504.2 GB/s of bandwidth. Clock speeds favor the desktop card dramatically. The RTX 4070 SUPER runs at a 1980 MHz base clock and 2475 MHz boost, while the RTX 4090 Mobile is rated at 1335 MHz base and 1695 MHz boost. Memory clocks also differ: 2250 MHz (18 Gbps effective) on the mobile card versus 1313 MHz (21 Gbps effective) on the desktop card.

Power delivery is a major differentiator. The RTX 4090 Mobile has a 120 W TDP and requires no power connectors, being an integrated graphics processor (IGP) with a form factor described as "Portable Device Dependent." The RTX 4070 SUPER is a dual-slot card with a 220 W TDP, a single 16-pin power connector, and a suggested 550 W power supply. Its physical dimensions are 267 mm in length, 112 mm in height, and 42 mm in width.

FAQ

Q: Which GPU has more raw compute power?

A: The RTX 4070 SUPER leads in FP32 performance at 35.48 TFLOPS, compared to the RTX 4090 Mobile's 32.98 TFLOPS. Both deliver identical FP16 performance at a 1:1 ratio with their FP32 figures.

Q: How do the memory systems compare?

A: The RTX 4090 Mobile has more capacity (16 GB vs 12 GB) and higher bandwidth (576.0 GB/s vs 504.2 GB/s) thanks to its 256-bit bus. However, the RTX 4070 SUPER uses faster GDDR6X memory at 21 Gbps effective, versus the mobile card's GDDR6 at 18 Gbps effective.

Q: Which card is more power-efficient?

A: The RTX 4090 Mobile is dramatically more power-efficient, with a 120 W TDP versus the RTX 4070 SUPER's 220 W TDP. This makes sense given the mobile card's integrated design with no power connectors, while the desktop card requires a 16-pin connector and a 550 W power supply.

Q: Which GPU wins in modern DirectX 12 workloads?

A: The RTX 4070 SUPER edges out the RTX 4090 Mobile in Passmark DirectX 12, scoring 110 versus 107, a 2.7% advantage. Both cards support DirectX 12 Ultimate (12_2).

Q: What about Vulkan performance?

A: The RTX 4070 SUPER dominates in Geekbench Vulkan with a score of 205624, beating the RTX 4090 Mobile's 170774 by 16.9%. Both cards support Vulkan 1.4.

Q: Are these cards in the same performance class?

A: Yes, the average benchmark scores are nearly identical: 43667 for the RTX 4090 Mobile and 43223 for the RTX 4070 SUPER. The RTX 4090 Mobile sits at the 84th percentile of all GPUs, while the RTX 4070 SUPER is at the 83rd, and they appear in each other's nearest rival lists with a delta of just 1%.

Specification Differences

| Specification | RTX 4090 Mobile | RTX 4070 SUPER |

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

| Chip | AD103 | AD104 |

| Generation | GeForce 40 Mobile | GeForce 40 |

| Transistors | 45,900 million | 35,800 million |

| Die Size | 379 mm² | 294 mm² |

| Transistor Density | 121.1M / mm² | 121.8M / mm² |

| Base Clock | 1335 MHz | 1980 MHz |

| Boost Clock | 1695 MHz | 2475 MHz |

| Memory Clock | 2250 MHz (18 Gbps effective) | 1313 MHz (21 Gbps effective) |

| Memory Size | 16 GB | 12 GB |

| Memory Type | GDDR6 | GDDR6X |

| Memory Bus Width | 256 bit | 192 bit |

| Memory Bandwidth | 576.0 GB/s | 504.2 GB/s |

| Shading Units | 9728 | 7168 |

| TMUs | 304 | 224 |

| ROPs | 112 | 80 |

| RT Cores | 76 | 56 |

| Tensor Cores | 304 | 224 |

| Pixel Rate | 189.8 GPixel/s | 198.0 GPixel/s |

| Texture Rate | 515.3 GTexel/s | 554.4 GTexel/s |

| FP32 | 32.98 TFLOPS | 35.48 TFLOPS |

| FP16 | 32.98 TFLOPS (1:1) | 35.48 TFLOPS (1:1) |

| TDP | 120 W | 220 W |

| Slot Width | IGP | Dual-slot |

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

| Suggested PSU | N/A | 550 W |

| Display Outputs | Portable Device Dependent | 1x HDMI 2.1, 3x DisplayPort 1.4a |

| Dimensions | N/A | 267 mm x 112 mm x 42 mm |

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

| Release Date | 2023-01-02 | 2024-01-16 |

| Predecessor | GeForce 30 Mobile | GeForce 30 |

| Successor | GeForce 50 Mobile | GeForce 50 |

| Launch MSRP | N/A | 599 USD |

Head-to-Head Benchmarks

The most lopsided result in the entire comparison is in Passmark GPU compute, where the RTX 4070 SUPER scores 17108 against the RTX 4090 Mobile's 12347. That is a 27.8% advantage for the desktop card, a massive gap that reflects its higher FP32 throughput and faster clock speeds. This result alone suggests the RTX 4070 SUPER is far better suited for compute-heavy workloads like rendering, physics simulations, and machine learning inference.

The Geekbench Vulkan test shows the next largest margin. Here, the RTX 4070 SUPER posts 205624 versus the RTX 4090 Mobile's 170774, a 16.9% lead. Vulkan is increasingly important in modern games and professional applications, so this victory carries real weight. The RTX 4070 SUPER also wins the 2D performance test convincingly, scoring 1184 in Passmark G2D against the mobile card's 984, another 16.9% gap.

In the DirectX legacy tests, the RTX 4070 SUPER maintains its edge, though by smaller margins. Passmark DirectX 9 shows 344 versus 310, a 9.9% win for the desktop card. DirectX 11 results are closer: 273 versus 262, a 4% advantage. DirectX 12 follows the same pattern at 110 versus 107, a 2.7% lead. The RTX 4070 SUPER also wins the crucial Passmark G3D test, which measures overall 3D graphics performance, with 29995 versus 27212, a 9.3% margin.

The RTX 4090 Mobile's victories are narrower but notable. Its best win comes in Geekbench OpenCL, where it scores 180831 against the RTX 4070 SUPER's 172795, a 4.7% lead. This suggests the mobile card's larger memory configuration and wider bus provide an advantage in certain OpenCL-accelerated workloads. The RTX 4090 Mobile also wins Passmark DirectX 10 with 173 versus 167, a modest 3.6% edge.

Overall, the pattern is clear: the RTX 4070 SUPER wins in 7 of 9 benchmarks and dominates in compute, Vulkan, and legacy DirectX tests, while the RTX 4090 Mobile holds only narrow leads in OpenCL and DirectX 10. The average scores being within 1% of each other, however, means that real-world differences will depend heavily on the specific application and API used.