NVIDIA GeForce RTX 4090 Mobile vs NVIDIA GeForce RTX 5090 SE Comparison

Head-to-Head Benchmarks

The NVIDIA GeForce RTX 4090 Mobile and the NVIDIA GeForce RTX 5090 SE belong to different generations, and the recorded data reflects a substantial performance gulf between them. The RTX 4090 Mobile has a full set of benchmark scores, while the RTX 5090 SE currently has no recorded benchmark entries, meaning the comparison relies primarily on architectural specifications and the 40-series card's measured performance against its own nearest rivals.

The RTX 4090 Mobile delivers an average benchmark score of 43,667 across its nine recorded tests. Its strongest result comes in Geekbench OpenCL with a score of 180,831, followed by Geekbench Vulkan at 170,774. In Passmark tests, the card scores 27,212 in G3D, 12,347 in GPU Compute, 984 in G2D, 310 in DirectX 9, 262 in DirectX 11, 173 in DirectX 10, and 107 in DirectX 12. These numbers place the RTX 4090 Mobile at the 84th percentile among all GPUs in the database.

The nearest rivals for the RTX 4090 Mobile show how tightly grouped its performance is. The NVIDIA RTX A6000 holds an average score of 44,075, which is 0.9% higher than the RTX 4090 Mobile, making it the only rival that beats the mobile card. The NVIDIA Quadro M6000 scores 43,301, a 0.8% deficit relative to the RTX 4090 Mobile. The NVIDIA GeForce RTX 5050 Mobile scores 43,268, also 0.9% behind, and the NVIDIA Quadro M6000 24 GB scores 43,262, trailing by 0.9% as well. The data shows that the RTX 4090 Mobile falls within a 1.8 percentage point band across all four nearest rivals, indicating competitive parity rather than a dominant lead.

The RTX 5090 SE, by contrast, has no benchmark scores in the database. Its average benchmark score is listed as 0, and its percentile versus all GPUs is 50, which corresponds to the median position by default rather than any measured performance. The nearest rivals array for the RTX 5090 SE is empty, so there is no comparative data to establish its standing. This absence of recorded measurements means the head-to-head comparison for the 5090 SE must be inferred from its hardware specifications, particularly its compute throughput and memory subsystem capabilities.

In raw compute terms, the RTX 5090 SE doubles the FP32 throughput of the RTX 4090 Mobile. The 5090 SE reaches 66.94 TFLOPS, while the 4090 Mobile delivers 32.98 TFLOPS. The same ratio applies to FP16, with the 5090 SE at 66.94 TFLOPS versus 32.98 TFLOPS for the 4090 Mobile, both operating at a 1:1 ratio. Pixel throughput also favors the 5090 SE substantially: 380.3 GPixel/s against 189.8 GPixel/s for the mobile card, a doubling of pixel fill rate. Texture rate shows an even larger gap, with the 5090 SE at 1,045.9 GTexel/s versus 515.3 GTexel/s for the 4090 Mobile.

The memory subsystem presents another decisive advantage for the 5090 SE. It uses 24 GB of GDDR7 memory on a 384-bit bus, yielding 1.34 TB/s of bandwidth. The RTX 4090 Mobile has 16 GB of GDDR6 on a 256-bit bus, providing 576.0 GB/s. The bandwidth difference is roughly 2.3 times in favor of the 5090 SE. Memory clock speeds also differ: the 5090 SE runs at 1750 MHz with 28 Gbps effective, while the 4090 Mobile runs at 2250 MHz with 18 Gbps effective. The newer GDDR7 standard in the 5090 SE compensates for the lower base clock through higher effective data rates.

The RTX 5090 SE also leads in shader resources. It has 14,080 shading units, 440 TMUs, and 160 ROPs, compared to 9,728 shading units, 304 TMUs, and 112 ROPs for the RTX 4090 Mobile. Ray tracing cores number 110 on the 5090 SE versus 76 on the 4090 Mobile, and tensor cores are 440 versus 304, respectively. These resource advantages translate directly into the higher fill rates and compute figures noted above.

Where Each One Wins

The RTX 4090 Mobile wins in portability and power efficiency. Its TDP is 120 W, while the RTX 5090 SE draws 500 W. The mobile card uses an IGP slot width with no power connectors, making it suitable for thin laptops. The 5090 SE is a dual-slot card requiring a single 16-pin power connector and a suggested PSU of 900 W. The physical dimensions also separate them: the 5090 SE measures 267 mm in length, 111 mm in height, and 40 mm in width, whereas the 4090 Mobile has no listed dimensions due to its integrated nature. The mobile card's display outputs are portable-device dependent, while the 5090 SE offers 1x HDMI 2.1b and 3x DisplayPort 2.1b.

The RTX 4090 Mobile also wins on the basis of having actual measured benchmark results. Its average score of 43,667 places it at the 84th percentile, and its nearest rivals confirm it sits near the top of the mobile GPU hierarchy. The recorded data shows the 4090 Mobile within 1% of several desktop workstation-class cards, including the Quadro M6000 and the RTX 5050 Mobile, and only 0.9% behind the RTX A6000. This indicates that the mobile part delivers desktop-class performance in a 120 W envelope.

The RTX 5090 SE wins in every raw performance metric available in the database. Its compute throughput, pixel rate, texture rate, memory capacity, memory bandwidth, and shader resource counts all exceed the RTX 4090 Mobile by significant margins. The 5090 SE doubles FP32 and FP16 throughput, doubles pixel fill rate, and more than doubles texture rate and memory bandwidth. Its 24 GB VRAM capacity exceeds the 16 GB of the 4090 Mobile by 50%, and its 384-bit bus width provides a wider memory path than the 256-bit bus on the mobile card.

For workloads that depend on memory bandwidth, such as high-resolution texture streaming or large dataset processing, the 5090 SE's 1.34 TB/s versus 576.0 GB/s represents a clear advantage. For compute-heavy tasks like ray tracing or tensor operations, the 5090 SE's 110 RT cores and 440 tensor cores outnumber the 76 RT cores and 304 tensor cores on the 4090 Mobile. The 5090 SE also supports PCIe 5.0 x16, while the 4090 Mobile uses PCIe 4.0 x16, doubling the potential CPU-to-GPU transfer bandwidth.

Architecture Differences

The two GPUs come from different architectural generations. The RTX 4090 Mobile uses the AD103 chip based on Ada Lovelace architecture, belonging to the GeForce 40-series and the GeForce 40 Mobile generation. The RTX 5090 SE uses the GB202 chip based on Blackwell 2.0 architecture, belonging to the GeForce 50-series and the GeForce 50 generation. Both are manufactured by TSMC on a 5 nm process node, but the chip sizes differ dramatically. The AD103 die measures 379 mm² with 45,900 million transistors, yielding a transistor density of 121.1M per mm². The GB202 die measures 750 mm² with 92,200 million transistors, yielding a density of 122.9M per mm². The GB202 die is nearly twice the size and holds roughly double the transistor count.

The memory technology differs as well. The RTX 4090 Mobile uses GDDR6, while the RTX 5090 SE uses GDDR7. The bus widths are 256-bit and 384-bit, respectively, and the memory capacities are 16 GB versus 24 GB. The clock speeds also diverge: the 4090 Mobile's base clock is 1335 MHz with a boost of 1695 MHz, while the 5090 SE's base clock is 1740 MHz with a boost of 2377 MHz. The boost clock advantage of 682 MHz on the 5090 SE contributes to its higher throughput.

Both cards support the same API feature set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The bus interface differs, with the 4090 Mobile using PCIe 4.0 x16 and the 5090 SE using PCIe 5.0 x16. The power delivery also contrasts sharply: the 4090 Mobile has no power connectors and a 120 W TDP, while the 5090 SE uses a single 16-pin connector, a 500 W TDP, and a suggested PSU of 900 W. The 5090 SE is a dual-slot card with physical dimensions of 267 mm by 111 mm by 40 mm, whereas the 4090 Mobile is classified as an IGP with no listed physical dimensions.

The release dates also differ. The RTX 4090 Mobile was released on 2023-01-02, while the RTX 5090 SE carries a release date of 2025-12-31. In the database's generation lineage, the 4090 Mobile lists its predecessor as GeForce 30 Mobile and its successor as GeForce 50 Mobile. The 5090 SE lists its predecessor as GeForce 40 and its successor as GeForce 60. This confirms the 5090 SE belongs to a newer product cycle.

FAQ

Q: Which GPU has the higher FP32 compute throughput?

A: The NVIDIA GeForce RTX 5090 SE delivers 66.94 TFLOPS in FP32, exactly double the 32.98 TFLOPS of the NVIDIA GeForce RTX 4090 Mobile.

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

A: The RTX 5090 SE provides 1.34 TB/s of bandwidth using 24 GB of GDDR7 on a 384-bit bus. The RTX 4090 Mobile provides 576.0 GB/s using 16 GB of GDDR6 on a 256-bit bus.

Q: How much power does each GPU consume?

A: The RTX 4090 Mobile has a TDP of 120 W with no power connectors. The RTX 5090 SE has a TDP of 500 W, requires a single 16-pin power connector, and has a suggested PSU of 900 W.

Q: Which GPU has more ray tracing cores?

A: The RTX 5090 SE has 110 RT cores, while the RTX 4090 Mobile has 76 RT cores. The RTX 5090 SE also has 440 tensor cores versus 304 on the RTX 4090 Mobile.

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

A: No, the database lists no benchmark entries for the RTX 5090 SE. Its average benchmark score is 0, and its percentile versus all GPUs is 50 by default. The RTX 4090 Mobile has nine recorded benchmark scores with an average of 43,667.

Q: What is the die size and transistor count for each chip?

A: The RTX 4090 Mobile uses the AD103 chip with a 379 mm² die and 45,900 million transistors. The RTX 5090 SE uses the GB202 chip with a 750 mm² die and 92,200 million transistors.

Specification Differences

| Specification | NVIDIA GeForce RTX 4090 Mobile | NVIDIA GeForce RTX 5090 SE |

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

| Chip | AD103 | GB202 |

| Architecture | Ada Lovelace | Blackwell 2.0 |

| Generation | GeForce 40 Mobile | GeForce 50 |

| Transistors | 45,900 million | 92,200 million |

| Die Size | 379 mm² | 750 mm² |

| Transistor Density | 121.1M / mm² | 122.9M / mm² |

| Base Clock | 1335 MHz | 1740 MHz |

| Boost Clock | 1695 MHz | 2377 MHz |

| Memory Clock | 2250 MHz, 18 Gbps effective | 1750 MHz, 28 Gbps effective |

| Memory Size | 16 GB | 24 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Bus Width | 256 bit | 384 bit |

| Memory Bandwidth | 576.0 GB/s | 1.34 TB/s |

| Shading Units | 9728 | 14080 |

| TMUs | 304 | 440 |

| ROPs | 112 | 160 |

| RT Cores | 76 | 110 |

| Tensor Cores | 304 | 440 |

| Pixel Rate | 189.8 GPixel/s | 380.3 GPixel/s |

| Texture Rate | 515.3 GTexel/s | 1,045.9 GTexel/s |

| FP32 | 32.98 TFLOPS | 66.94 TFLOPS |

| FP16 | 32.98 TFLOPS (1:1) | 66.94 TFLOPS (1:1) |

| TDP | 120 W | 500 W |

| Slot Width | IGP | Dual-slot |

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

| Suggested PSU | Not specified | 900 W |

| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |

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

| Dimensions | Not specified | 267 mm x 111 mm x 40 mm |

| Release Date | 2023-01-02 | 2025-12-31 |

| Launch MSRP | Not specified | 1,499 USD |

| Predecessor | GeForce 30 Mobile | GeForce 40 |

| Successor | GeForce 50 Mobile | GeForce 60 |

| Production Status | Active | Active |