NVIDIA GeForce RTX 4090 Mobile vs NVIDIA N1X 48SM Comparison

FAQ

Q: How does the NVIDIA GeForce RTX 4090 Mobile compare to the NVIDIA N1X 48SM in raw compute performance?

A: The RTX 4090 Mobile delivers 32.98 TFLOPS of FP32 compute, while the N1X 48SM provides 28.83 TFLOPS. The RTX 4090 Mobile leads by roughly 4.15 TFLOPS, or about 14% higher peak shader throughput.

Q: What memory configurations do these two GPUs use?

A: The RTX 4090 Mobile uses 16 GB of GDDR6 on a 256-bit bus with 576.0 GB/s of bandwidth. The N1X 48SM uses 128 GB of LPDDR5X on a 256-bit bus with 273.2 GB/s of bandwidth.

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

A: The RTX 4090 Mobile has 9728 shading units and 76 RT cores. The N1X 48SM has 6144 shading units and 48 RT cores. The RTX 4090 Mobile holds a 3584-unit advantage in shaders and a 28-core advantage in RT cores.

Q: What are the clock speeds for each GPU?

A: The RTX 4090 Mobile has a base clock of 1335 MHz and a boost clock of 1695 MHz. The N1X 48SM has a base clock of 741 MHz and a boost clock of 2346 MHz.

Q: Which architecture does each GPU use, and what process node?

A: The RTX 4090 Mobile uses the Ada Lovelace architecture on a 5 nm process with the AD103 chip. The N1X 48SM uses the Blackwell 2.0 architecture on a 5 nm process with the GB20B chip. Both are fabricated by TSMC.

Q: What is the average benchmark score for each GPU?

A: The RTX 4090 Mobile has an average benchmark score of 43667 and sits in the 84th percentile of all GPUs. The N1X 48SM has an average benchmark score of 0 and sits in the 50th percentile, with no recorded benchmarks in the database.

Architecture Differences

The RTX 4090 Mobile is built on Ada Lovelace, NVIDIA's architecture for the GeForce 40 Mobile generation. It uses the AD103 chip with 45,900 million transistors on a 379 mm² die, yielding a transistor density of 121.1M per mm². The N1X 48SM uses the Blackwell 2.0 architecture with the GB20B chip, and while its transistor count is unknown, its die size is 382 mm², slightly larger than the RTX 4090 Mobile.

Both GPUs are manufactured on a 5 nm process at TSMC. The RTX 4090 Mobile is part of the GeForce 40 Mobile generation and is the predecessor to the GeForce 50 Mobile series. The N1X 48SM belongs to the Blackwell IGP (N1x) generation and has no listed predecessor or successor.

The shader configuration differs substantially. The RTX 4090 Mobile uses 9728 shading units, 304 TMUs, and 112 ROPs. The N1X 48SM uses 6144 shading units, 384 TMUs, and 48 ROPs. This means the RTX 4090 Mobile has 3584 more shaders and 64 more ROPs, while the N1X 48SM has 80 more TMUs.

Ray tracing and tensor core counts also favor the RTX 4090 Mobile. It has 76 RT cores and 304 tensor cores, versus 48 RT cores and 192 tensor cores on the N1X 48SM. The RTX 4090 Mobile therefore holds a 28-core lead in RT cores and a 112-core lead in tensor cores.

The memory subsystem represents a clear divergence. The RTX 4090 Mobile uses 16 GB of GDDR6 with a 256-bit bus and 576.0 GB/s bandwidth. The N1X 48SM uses 128 GB of LPDDR5X with a 256-bit bus but only 273.2 GB/s bandwidth. The RTX 4090 Mobile delivers more than double the memory bandwidth, while the N1X 48SM offers eight times the capacity.

Clock behavior differs significantly. The RTX 4090 Mobile runs at a base clock of 1335 MHz and a boost clock of 1695 MHz. The N1X 48SM runs at a base clock of 741 MHz and a boost clock of 2346 MHz. The N1X 48SM has a higher boost clock by 651 MHz, but its base clock is 594 MHz lower.

The bus interface also differs. The RTX 4090 Mobile uses PCIe 4.0 x16, while the N1X 48SM uses PCIe 5.0 x16. Display outputs vary as well: the RTX 4090 Mobile is listed as portable device dependent, while the N1X 48SM has 1x HDMI.

API support diverges sharply. The RTX 4090 Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The N1X 48SM lists all APIs as N/A.

The Verdict

The benchmark data favors the RTX 4090 Mobile decisively. Its average benchmark score of 43667 places it in the 84th percentile of all GPUs, while the N1X 48SM has no recorded benchmark scores and sits in the 50th percentile. The RTX 4090 Mobile also edges out several known rivals: it is 0.8% ahead of the NVIDIA Quadro M6000, 0.9% ahead of the GeForce RTX 5050 Mobile, 0.9% ahead of the Quadro M6000 24 GB, and only 0.9% behind the RTX A6000.

The RTX 4090 Mobile is the clear choice for any workload that depends on shader throughput, ray tracing, or memory bandwidth. It delivers 32.98 TFLOPS of FP32 compute against 28.83 TFLOPS for the N1X 48SM, and its 576.0 GB/s memory bandwidth dwarfs the 273.2 GB/s of the N1X 48SM. For gaming, real-time rendering, or compute tasks that rely on high bandwidth, the RTX 4090 Mobile is the stronger part.

The N1X 48SM offers a different trade-off. Its 128 GB of LPDDR5X memory is eight times the capacity of the RTX 4090 Mobile, and its 384 TMUs exceed the 304 TMUs on the RTX 4090 Mobile. The N1X 48SM also has a higher boost clock at 2346 MHz versus 1695 MHz, which contributes to its texture rate of 900.9 GTexel/s, well above the 515.3 GTexel/s of the RTX 4090 Mobile.

For users who need massive memory capacity or texture-heavy workloads that scale with TMU count, the N1X 48SM has a role. But the absence of any recorded benchmarks and the N/A API support make its real-world performance unverified. The RTX 4090 Mobile is the proven performer with a measurable track record.

Specification Differences

| Specification | RTX 4090 Mobile | N1X 48SM |

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

| Architecture | Ada Lovelace | Blackwell 2.0 |

| Chip | AD103 | GB20B |

| Generation | GeForce 40 Mobile | Blackwell IGP (N1x) |

| Transistors | 45,900 million | unknown |

| Die Size | 379 mm² | 382 mm² |

| Transistor Density | 121.1M / mm² | null |

| Base Clock | 1335 MHz | 741 MHz |

| Boost Clock | 1695 MHz | 2346 MHz |

| Memory Size | 16 GB | 128 GB |

| Memory Type | GDDR6 | LPDDR5X |

| Memory Bus | 256 bit | 256 bit |

| Memory Bandwidth | 576.0 GB/s | 273.2 GB/s |

| Shading Units | 9728 | 6144 |

| TMUs | 304 | 384 |

| ROPs | 112 | 48 |

| RT Cores | 76 | 48 |

| Tensor Cores | 304 | 192 |

| Pixel Rate | 189.8 GPixel/s | 112.6 GPixel/s |

| Texture Rate | 515.3 GTexel/s | 900.9 GTexel/s |

| FP32 | 32.98 TFLOPS | 28.83 TFLOPS |

| FP16 | 32.98 TFLOPS (1:1) | 28.83 TFLOPS (1:1) |

| TDP | 120 W | unknown |

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

| Display Outputs | Portable Device Dependent | 1x HDMI |

| DirectX | 12 Ultimate (12_2) | N/A |

| OpenGL | 4.6 | N/A |

| Vulkan | 1.4 | N/A |

| Release Date | 2023-01-02 | 2026-05-31 |

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries for these two GPUs, and the N1X 48SM has no individual benchmark records. The comparison therefore relies on the recorded metrics for the RTX 4090 Mobile and the stated specifications for both parts.

The RTX 4090 Mobile posts an average benchmark score of 43667. Its individual results include 180831 in Geekbench OpenCL, 170774 in Geekbench Vulkan, 27212 in Passmark G3D, and 12347 in Passmark GPU Compute. It also records 984 in Passmark G2D, 310 in Passmark DirectX 9, 262 in Passmark DirectX 11, 173 in Passmark DirectX 10, and 107 in Passmark DirectX 12.

The N1X 48SM has no recorded benchmark scores, making direct numerical comparison impossible. However, the specification data provides a basis for expected differences. The RTX 4090 Mobile leads in FP32 compute by 4.15 TFLOPS, in pixel rate by 77.2 GPixel/s, and in memory bandwidth by 302.8 GB/s. The N1X 48SM leads in texture rate by 385.6 GTexel/s and in boost clock by 651 MHz.

The RTX 4090 Mobile also has a substantial advantage in shading units, with 9728 versus 6144, a 58% lead. Its RT core count of 76 is 58% higher than the 48 on the N1X 48SM. The tensor core advantage is similar, with 304 versus 192.

Where Each One Wins

The RTX 4090 Mobile wins in compute-heavy scenarios. Its FP32 throughput of 32.98 TFLOPS exceeds the 28.83 TFLOPS of the N1X 48SM, and its 576.0 GB/s bandwidth is more than double the 273.2 GB/s of the N1X 48SM. Workloads that depend on raw shader arithmetic, such as general-purpose GPU compute or rasterized rendering, will favor the RTX 4090 Mobile.

The RTX 4090 Mobile also wins in ray tracing and tensor operations. With 76 RT cores versus 48 and 304 tensor cores versus 192, it offers more hardware resources for these specialized paths. Its pixel rate of 189.8 GPixel/s versus 112.6 GPixel/s further reinforces its advantage in fill-rate-bound scenes.

The N1X 48SM wins in memory capacity. Its 128 GB of LPDDR5X is eight times the 16 GB of the RTX 4090 Mobile. For workloads that require holding very large datasets on the GPU, such as certain scientific or data-processing tasks, the N1X 48SM provides a capacity advantage that the RTX 4090 Mobile cannot match.

The N1X 48SM also wins in texture throughput. Its 384 TMUs and 2346 MHz boost clock yield a texture rate of 900.9 GTexel/s, versus 515.3 GTexel/s for the RTX 4090 Mobile. Texture-heavy workloads that scale with TMU count and clock speed may perform better on the N1X 48SM, assuming driver and API support become available.

The N1X 48SM has a newer bus interface, PCIe 5.0 x16, compared to PCIe 4.0 x16 on the RTX 4090 Mobile. This could matter for data transfer to and from the host system, though the RTX 4090 Mobile compensates with far higher memory bandwidth.

The RTX 4090 Mobile is the better choice for established gaming and graphics applications, given its DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4 support. The N1X 48SM lists all APIs as N/A, meaning its compatibility with existing software is unproven. The RTX 4090 Mobile also has a proven track record with a measurable average score of 43667, while the N1X 48SM has no benchmark evidence.