NVIDIA GeForce RTX 4070 Mobile vs NVIDIA GeForce RTX 5090 SE Comparison

Head-to-Head Benchmarks

The database contains a full benchmark suite for the NVIDIA GeForce RTX 4070 Mobile, while the RTX 5090 SE has no recorded benchmark scores at this time. This makes a direct numerical comparison of performance impossible. However, the available hardware specifications and the RTX 4070 Mobile's recorded results allow for a meaningful analysis of what the RTX 5090 SE is designed to deliver.

The RTX 4070 Mobile posts an average benchmark score of 27,435 across all tests. Its strongest result comes from Geekbench OpenCL with 109,197 points, closely followed by Geekbench Vulkan with 108,367 points. In the Passmark suite, the G3D score of 19,587 is the highest DirectX-related result, while the GPU compute score reaches 8,399. The lower-level Passmark tests show results of 223 in DirectX 9, 179 in DirectX 11, and 116 in DirectX 10, with the DirectX 12 test scoring 85. The 2D graphics score is 763.

The RTX 4070 Mobile's average benchmark score places it in the 73rd percentile of all GPUs in the database. Its nearest rivals are tightly clustered: the AMD Radeon RX 6700 XT scores 27,425 (0% delta), the NVIDIA GeForce RTX 3090 scores 27,565 (-0.5% delta), the NVIDIA RTX PRO 4000 Blackwell scores 27,135 (1.1% delta), and the AMD Radeon Pro Vega 20 scores 27,839 (-1.5% delta). The data shows the RTX 4070 Mobile is effectively performance-neutral against all four rivals, with deltas ranging from -1.5% to +1.1%. The RTX 4070 Mobile sits just 130 points below the RTX 3090 and only 404 points above the RTX PRO 4000 Blackwell.

The RTX 5090 SE has no benchmark entries in the database, so its percentile ranking of 50 reflects an absence of data rather than a performance assessment. Its average benchmark score is recorded as 0. The head-to-head comparison table between the two cards shows no tests and no wins for either side.

Despite the lack of RTX 5090 SE scores, the specification gap between the two cards is substantial. The RTX 5090 SE uses the GB202 chip with 92,200 million transistors, while the RTX 4070 Mobile uses the AD106 chip with 22,900 million transistors. That is a 4.0x difference in transistor count. The RTX 5090 SE's die size of 750 mm² compared to 188 mm² for the RTX 4070 Mobile represents a 4.0x difference in physical area. Transistor density is nearly identical: 122.9M per mm² for the RTX 5090 SE versus 121.8M per mm² for the RTX 4070 Mobile.

The shading unit count shows the scale of the difference: the RTX 5090 SE has 14,080 shading units versus 4,608 for the RTX 4070 Mobile, a 3.1x advantage. Texture mapping units number 440 versus 144 (3.1x), and render output units number 160 versus 48 (3.3x). Ray tracing cores are 110 versus 36 (3.1x), and tensor cores are 440 versus 144 (3.1x).

Clock speeds also favor the RTX 5090 SE. Its base clock of 1740 MHz is 345 MHz higher than the RTX 4070 Mobile's 1395 MHz. The boost clock of 2377 MHz exceeds the RTX 4070 Mobile's 1695 MHz by 682 MHz. These higher clocks, combined with the massive increase in core counts, produce dramatically higher theoretical throughput. The RTX 5090 SE's FP32 performance is 66.94 TFLOPS versus 15.62 TFLOPS for the RTX 4070 Mobile, a 4.3x difference. FP16 performance shows the same ratio at 66.94 TFLOPS versus 15.62 TFLOPS (1:1 in both cases). Pixel rate is 380.3 GPixel/s versus 81.36 GPixel/s (4.7x), and texture rate is 1,045.9 GTexel/s versus 244.1 GTexel/s (4.3x).

Memory capacity and bandwidth follow the same pattern. The RTX 5090 SE has 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s bandwidth. The RTX 4070 Mobile has 8 GB of GDDR6 memory on a 128-bit bus with 256.0 GB/s bandwidth. The memory bandwidth difference is 5.2x in favor of the RTX 5090 SE. Effective memory speed is 28 Gbps for the RTX 5090 SE versus 16 Gbps for the RTX 4070 Mobile.

The Verdict

The benchmark data shows the RTX 4070 Mobile is a competent mid-range mobile GPU. Its 73rd percentile ranking and tight clustering with desktop cards like the RTX 3090 and RX 6700 XT indicate it holds its own in the database's performance hierarchy. The narrow deltas, all within 1.5% of its average score, suggest the RTX 4070 Mobile delivers consistent, predictable performance relative to its nearest rivals.

The RTX 5090 SE, by contrast, has no verified performance data in the database. The specification sheet indicates a GPU designed for a completely different performance tier. With 4.3x the FP32 throughput, 5.2x the memory bandwidth, and 3x the memory capacity of the RTX 4070 Mobile, the RTX 5090 SE is positioned as a high-end desktop solution while the RTX 4070 Mobile is a mobile part with a lower power envelope.

The power requirements reinforce this distinction. The RTX 5090 SE has a TDP of 500 W, requires a 900 W suggested PSU, and uses a dual-slot cooler with a 16-pin connector. The RTX 4070 Mobile has a TDP of 115 W, uses no power connectors, and is listed as IGP (integrated graphics package) with portable device dependent display outputs. These are different product categories with different design goals.

For users seeking a mobile GPU that delivers desktop-class performance in a notebook form factor, the RTX 4070 Mobile's recorded benchmarks show it is competitive with the RX 6700 XT, RTX 3090, RTX PRO 4000 Blackwell, and Radeon Pro Vega 20. The percentile ranking of 73 confirms it outperforms most GPUs in the database.

For users considering the RTX 5090 SE, the database currently offers no performance confirmation. The specifications indicate a GPU that should dramatically outperform the RTX 4070 Mobile in every measurable category, but until benchmark scores are recorded, the actual performance delta remains unverified. The launch MSRP for the RTX 5090 SE is 1,499 USD, and it is listed as active with a release date of 2025-12-31.

FAQ

Q: How does the RTX 4070 Mobile compare to its nearest rivals in the database?

A: The RTX 4070 Mobile's average benchmark score of 27,435 is within 1.5% of all four nearest rivals. It is 10 points above the AMD Radeon RX 6700 XT (27,425), 130 points below the NVIDIA GeForce RTX 3090 (27,565), 300 points above the NVIDIA RTX PRO 4000 Blackwell (27,135), and 404 points below the AMD Radeon Pro Vega 20 (27,839).

Q: Does the RTX 5090 SE have any benchmark scores in the database?

A: No. The RTX 5090 SE has an empty benchmark list, an average benchmark score of 0, and a percentile ranking of 50, which reflects missing data rather than measured performance.

Q: What is the memory configuration difference between the two cards?

A: The RTX 5090 SE uses 24 GB of GDDR7 memory on a 384-bit bus with 1.34 TB/s bandwidth and 28 Gbps effective speed. The RTX 4070 Mobile uses 8 GB of GDDR6 memory on a 128-bit bus with 256.0 GB/s bandwidth and 16 Gbps effective speed.

Q: How do the physical dimensions differ?

A: The RTX 5090 SE is a dual-slot card measuring 267 mm in length, 111 mm in height, and 40 mm in width. The RTX 4070 Mobile has no listed dimensions and is classified as IGP with portable device dependent display outputs.

Q: What are the power requirements for each card?

A: The RTX 5090 SE has a TDP of 500 W, uses a 1x 16-pin power connector, and requires a suggested PSU of 900 W. The RTX 4070 Mobile has a TDP of 115 W and uses no power connectors.

Q: Which card has a higher transistor density?

A: The RTX 5090 SE has a transistor density of 122.9M per mm², slightly higher than the RTX 4070 Mobile's 121.8M per mm². Both use TSMC's 5 nm process node.

Specification Differences

The two cards differ across nearly every specification field in the database. The RTX 4070 Mobile uses the AD106 chip with 22,900 million transistors on a 188 mm² die. The RTX 5090 SE uses the GB202 chip with 92,200 million transistors on a 750 mm² die.

Clock speeds differ substantially: the RTX 4070 Mobile has a base clock of 1395 MHz and a boost clock of 1695 MHz, while the RTX 5090 SE has a base clock of 1740 MHz and a boost clock of 2377 MHz.

Memory specifications diverge completely: the RTX 4070 Mobile has 8 GB GDDR6 with a 128-bit bus and 256.0 GB/s bandwidth, while the RTX 5090 SE has 24 GB GDDR7 with a 384-bit bus and 1.34 TB/s bandwidth. Memory speed is 16 Gbps effective versus 28 Gbps effective.

The compute configuration shows the RTX 5090 SE with 14,080 shading units, 440 TMUs, 160 ROPs, 110 RT cores, and 440 tensor cores. The RTX 4070 Mobile has 4,608 shading units, 144 TMUs, 48 ROPs, 36 RT cores, and 144 tensor cores.

Output rates: the RTX 5090 SE achieves a pixel rate of 380.3 GPixel/s and a texture rate of 1,045.9 GTexel/s, compared to 81.36 GPixel/s and 244.1 GTexel/s for the RTX 4070 Mobile. FP32 and FP16 throughput are both 66.94 TFLOPS for the RTX 5090 SE versus 15.62 TFLOPS for the RTX 4070 Mobile.

Power and physical specifications differ sharply. The RTX 5090 SE has a TDP of 500 W, is dual-slot, uses a 1x 16-pin power connector, and requires a 900 W suggested PSU. The RTX 4070 Mobile has a TDP of 115 W, is IGP, uses no power connectors, and has no suggested PSU.

Bus interface: the RTX 5090 SE uses PCIe 5.0 x16, while the RTX 4070 Mobile uses PCIe 4.0 x8. Display outputs: the RTX 5090 SE has 1x HDMI 2.1b and 3x DisplayPort 2.1b, while the RTX 4070 Mobile's outputs are portable device dependent.

Release dates: the RTX 4070 Mobile launched on 2023-01-02, while the RTX 5090 SE has a release date of 2025-12-31. Both are listed as Active in production status.

Architecture Differences

The RTX 4070 Mobile is built on the Ada Lovelace architecture, part of the GeForce 40-series and the GeForce 40 Mobile generation. The RTX 5090 SE uses the Blackwell 2.0 architecture, part of the GeForce 50-series and the GeForce 50 generation.

Both chips are fabricated on TSMC's 5 nm process node, but the die sizes diverge dramatically: 188 mm² for the AD106 chip versus 750 mm² for the GB202 chip. Transistor counts are 22,900 million versus 92,200 million, with nearly identical densities of 121.8M per mm² and 122.9M per mm² respectively.

The core architecture differs in scale. The RTX 5090 SE's 110 ray tracing cores and 440 tensor cores represent a 3.1x increase over the RTX 4070 Mobile's 36 RT cores and 144 tensor cores. The shading unit count of 14,080 versus 4,608, TMU count of 440 versus 144, and ROP count of 160 versus 48 all follow the same 3.1x to 3.3x pattern.

Memory architecture is a significant departure. The RTX 5090 SE uses GDDR7 memory with a 384-bit bus, while the RTX 4070 Mobile uses GDDR6 with a 128-bit bus. The resulting bandwidth of 1.34 TB/s versus 256.0 GB/s represents a 5.2x difference, which is larger than the core count differences.

The API support is identical: both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

The RTX 4070 Mobile's predecessor is the GeForce 30 Mobile series, and its successor is the GeForce 50 Mobile series. The RTX 5090 SE's predecessor is the GeForce 40 series, and its successor is the GeForce 60 series.

The power architecture shows the fundamental design difference: the RTX 5090 SE is a desktop-oriented dual-slot card with a 500 W TDP and external power delivery, while the RTX 4070 Mobile is an integrated mobile GPU with a 115 W TDP and no power connector, indicating it draws power through the host system.