NVIDIA GeForce RTX 4070 Ti SUPER vs NVIDIA GeForce RTX 4080 Mobile Comparison

The Verdict

The benchmark data splits these two NVIDIA GeForce 40-series parts into very different roles. The RTX 4080 Mobile wins only one of nine head-to-head tests, while the RTX 4070 Ti SUPER wins eight. However, the lone victory for the mobile part is massive: a 171.6% lead in Geekbench Vulkan, a result that completely changes the interpretation. The RTX 4070 Ti SUPER is the dominant choice for raw compute and legacy DirectX workloads, but the RTX 4080 Mobile shows a specialized strength in Vulkan that cannot be ignored. For users who prioritize modern API performance in a portable form factor, the data points to the RTX 4080 Mobile. For everything else, especially compute-heavy tasks and older DirectX titles, the RTX 4070 Ti SUPER is clearly the stronger performer. The database also shows a higher average benchmark score for the RTX 4080 Mobile at 38135 versus 31087 for the RTX 4070 Ti SUPER, despite the latter winning more individual tests, which suggests the mobile part's Vulkan outlier heavily influences its aggregate standing. The RTX 4070 Ti SUPER sits at the 76th percentile among all GPUs, while the RTX 4080 Mobile sits higher at the 81st percentile, reinforcing that the mobile part's overall profile is better when averaged across all recorded tests.

Architecture Differences

Both GPUs are built on TSMC's 5 nm process and use the Ada Lovelace architecture, but they are distinct chips with different configurations. The RTX 4080 Mobile uses the AD104 chip with 35,800 million transistors on a 294 mm² die, while the RTX 4070 Ti SUPER uses the larger AD103 chip with 45,900 million transistors on a 379 mm² die. Transistor density is nearly identical: 121.8M per mm² for the mobile part versus 121.1M per mm² for the desktop card. The RTX 4070 Ti SUPER has more of everything in terms of execution resources: 8448 shading units versus 7424, 264 texture mapping units versus 232, 96 ROPs versus 80, 66 ray tracing cores versus 58, and 264 tensor cores versus 232. Clock speeds favor the desktop card dramatically, with a base clock of 2340 MHz and boost of 2610 MHz, compared to the mobile part's 1290 MHz base and 1665 MHz boost. Memory differs both in type and configuration: the RTX 4080 Mobile uses 12 GB of GDDR6 on a 192-bit bus with 432.0 GB/s bandwidth, while the RTX 4070 Ti SUPER uses 16 GB of GDDR6X on a 256-bit bus with 672.3 GB/s bandwidth. The memory clock is 2250 MHz (18 Gbps effective) for the mobile part versus 1313 MHz (21 Gbps effective) for the desktop card. Power consumption is another major divider: the RTX 4080 Mobile has a TDP of 110 W and uses no external power connectors, while the RTX 4070 Ti SUPER draws 285 W and requires a single 16-pin connector with a suggested PSU of 600 W. The mobile part is an IGP (integrated graphics package) with display outputs described as portable device dependent, while the desktop card is a triple-slot design measuring 310 mm by 140 mm by 61 mm, with outputs of 1x HDMI 2.1 and 3x DisplayPort 1.4a. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, and both use a PCIe 4.0 x16 interface.

Head-to-Head Benchmarks

The Geekbench OpenCL test shows the RTX 4070 Ti SUPER scoring 199267 against the RTX 4080 Mobile's 159575, a 19.9% advantage for the desktop card. This is a substantial lead and aligns with the raw computing power expected from the larger chip. The Vulkan test flips the script entirely: the RTX 4080 Mobile scores 145807 while the RTX 4070 Ti SUPER scores only 53683, giving the mobile part a 171.6% lead. This is the single largest delta in either direction across all tests and indicates a fundamental difference in how these two GPUs handle the Vulkan API in the recorded workloads. The Passmark suite consistently favors the RTX 4070 Ti SUPER. In DirectX 10, the desktop card wins 181 to 157, a 13.3% gap. DirectX 11 shows a 278 to 244 result, a 12.2% lead for the RTX 4070 Ti SUPER. DirectX 12 continues the trend with 119 versus 96, a 19.3% difference. DirectX 9 sees the widest margin among the DirectX tests: 360 to 286, a 20.6% advantage. The 2D graphics test (Passmark G2D) also goes to the RTX 4070 Ti SUPER at 1225 versus 929, a 24.2% lead. The main 3D graphics test (Passmark G3D) records 31811 for the desktop card against 24926 for the mobile part, a 21.6% gap. The compute test shows the largest overall margin for the RTX 4070 Ti SUPER: 18372 versus 11191, a 39.1% lead. Across nine tests, the RTX 4070 Ti SUPER wins eight, with the RTX 4080 Mobile taking only the Vulkan test. The average benchmark score for the RTX 4080 Mobile is 38135, which is higher than the RTX 4070 Ti SUPER's 31087, a result that appears counterintuitive given the individual test losses. The explanation lies in the Vulkan outlier and the weighting of the average calculation, which the database records without further detail.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce RTX 4080 Mobile has an average benchmark score of 38135, while the NVIDIA GeForce RTX 4070 Ti SUPER has an average score of 31087.

Q: What is the single largest performance difference between the two?

A: In the Geekbench Vulkan test, the RTX 4080 Mobile leads by 171.6%, scoring 145807 versus 53683 for the RTX 4070 Ti SUPER.

Q: How do the memory configurations differ?

A: The RTX 4080 Mobile uses 12 GB of GDDR6 on a 192-bit bus with 432.0 GB/s bandwidth. The RTX 4070 Ti SUPER uses 16 GB of GDDR6X on a 256-bit bus with 672.3 GB/s bandwidth.

Q: Which GPU has more shading units and ray tracing cores?

A: The RTX 4070 Ti SUPER has 8448 shading units and 66 ray tracing cores. The RTX 4080 Mobile has 7424 shading units and 58 ray tracing cores.

Q: What are the power requirements for each card?

A: The RTX 4080 Mobile has a TDP of 110 W and uses no power connectors. The RTX 4070 Ti SUPER has a TDP of 285 W, requires a single 16-pin power connector, and has a suggested PSU of 600 W.

Q: Which GPU is at a higher percentile among all GPUs?

A: The RTX 4080 Mobile is at the 81st percentile, while the RTX 4070 Ti SUPER is at the 76th percentile.

Where Each One Wins

The RTX 4070 Ti SUPER wins across almost the entire benchmark suite. It leads in Geekbench OpenCL by 19.9%, in every Passmark DirectX test (10, 11, 12, and 9) with margins between 12.2% and 20.6%, in Passmark G2D by 24.2%, in Passmark G3D by 21.6%, and in Passmark GPU Compute by 39.1%. This makes it the clear choice for workloads that rely on OpenCL compute, legacy DirectX APIs, 2D graphics operations, and general 3D rendering. The compute lead is particularly notable, suggesting the RTX 4070 Ti SUPER is better suited for tasks like rendering, scientific simulation, or any GPU-accelerated workload that maps to the compute test. The desktop card also has a much higher boost clock at 2610 MHz versus 1665 MHz, which likely contributes to its consistent wins in these tests. The RTX 4080 Mobile wins only the Geekbench Vulkan test, but this is a decisive victory at 171.6%. For applications that use the Vulkan API, the mobile part delivers dramatically better performance in the recorded data. This could indicate architectural or driver-level optimization differences that favor the mobile chip in Vulkan workloads, or it could reflect the specific benchmark implementation. The RTX 4080 Mobile also has a higher percentile ranking at 81 versus 76 and a higher average benchmark score, which means that when all tests are considered together, the mobile part's aggregate standing is better. Users who primarily run Vulkan-based games or applications should consider the RTX 4080 Mobile despite its losses elsewhere, as that single API can dominate real-world usage.

Specification Differences

The two GPUs differ across nearly every major specification field. The chip is different: AD104 for the RTX 4080 Mobile versus AD103 for the RTX 4070 Ti SUPER. Transistor count is 35,800 million versus 45,900 million, and die size is 294 mm² versus 379 mm². Transistor density is nearly the same at 121.8M per mm² versus 121.1M per mm². Base clocks are 1290 MHz versus 2340 MHz, and boost clocks are 1665 MHz versus 2610 MHz. Memory size is 12 GB versus 16 GB, memory type is GDDR6 versus GDDR6X, bus width is 192 bit versus 256 bit, and bandwidth is 432.0 GB/s versus 672.3 GB/s. Memory clock is 2250 MHz (18 Gbps effective) versus 1313 MHz (21 Gbps effective). Shading units are 7424 versus 8448, texture mapping units are 232 versus 264, ROPs are 80 versus 96, ray tracing cores are 58 versus 66, and tensor cores are 232 versus 264. Pixel rate is 133.2 GPixel/s versus 250.6 GPixel/s, texture rate is 386.3 GTexel/s versus 689.0 GTexel/s, and FP32 performance is 24.72 TFLOPS versus 44.10 TFLOPS. FP16 is also 24.72 TFLOPS versus 44.10 TFLOPS. TDP is 110 W versus 285 W. Slot width is IGP versus triple-slot. Power connectors are none versus 1x 16-pin. Suggested PSU is absent for the mobile part versus 600 W for the desktop card. Display outputs are portable device dependent versus 1x HDMI 2.1 and 3x DisplayPort 1.4a. Dimensions are not recorded for the mobile part, while the desktop card measures 310 mm by 140 mm by 61 mm. Release dates are January 2023 for the mobile part and January 2024 for the desktop card. The production status is active for the RTX 4080 Mobile and end-of-life for the RTX 4070 Ti SUPER. The launch MSRP for the RTX 4070 Ti SUPER is 799 USD; no launch MSRP is recorded for the RTX 4080 Mobile.