Intel Arc Pro B370 vs NVIDIA N1 16SM Comparison

Where Each One Wins

The Intel Arc Pro B370 and NVIDIA N1 16SM target entirely different use cases, and the recorded data makes that split explicit. The Intel part is an integrated GPU built for the Panther Lake mobile platform, with a DirectX 12 Ultimate feature set, OpenGL 4.6, and Vulkan 1.4 support. The NVIDIA N1 16SM is also an integrated part, but it is a Blackwell IGP for the N1x generation with no DirectX, OpenGL, or Vulkan support listed in the database. That single difference dictates where each one wins.

The Intel Arc Pro B370 wins in any scenario that requires modern graphics API compatibility. Its 12 Ultimate (12_2) DirectX support means it can run contemporary games and applications that expect Shader Model 6.6 or similar features. The NVIDIA N1 16SM cannot participate in those workloads at all, as its API support is marked as N/A across the board. For portable devices, the Intel part uses system-shared memory, while the NVIDIA part brings 128 GB of dedicated LPDDR5X memory on a 256-bit bus. The NVIDIA part wins in memory capacity and bandwidth, with 273.2 GB/s versus the Intel part's system-dependent bandwidth.

The NVIDIA N1 16SM also wins on raw compute throughput. Its FP32 rating of 9.609 TFLOPS is substantially higher than the Intel Arc Pro B370's 6.144 TFLOPS. Texture rate favors NVIDIA heavily at 300.3 GTexel/s versus 96.00 GTexel/s, and pixel rate favors NVIDIA at 56.30 GPixel/s versus 48.00 GPixel/s. The NVIDIA part also has more shading units (2048 vs 1280), more TMUs (128 vs 40), more ROPs (24 vs 20), more RT cores (16 vs 10), and 64 tensor cores where the Intel part lists none.

The Intel Arc Pro B370 wins on efficiency metrics and integration simplicity. Its TDP is rated at 25 W, while the NVIDIA part's TDP is unknown in the database. The Intel part uses a 3 nm process node from Intel's own foundry, while the NVIDIA part uses a 5 nm node from TSMC. The Intel part has a higher boost clock at 2400 MHz versus 2346 MHz, and its base clock is 300 MHz versus 741 MHz for NVIDIA, though the NVIDIA part's higher base clock does not compensate for its lower boost ceiling. The Intel part also lists a production status of Active and a release date of January 2026, while the NVIDIA part is also Active with a later release date of May 2026.

Architecture Differences

The two GPUs come from different architectural lineages. The Intel Arc Pro B370 uses the Xe3-LPG architecture on the Panther Lake chip, part of the Arc Graphics-WM generation. The NVIDIA N1 16SM uses the Blackwell 2.0 architecture on the GB20B chip, part of the Blackwell IGP (N1x) generation. The process nodes differ: Intel uses 3 nm silicon from its own foundry, while NVIDIA uses 5 nm silicon from TSMC. The die size for the NVIDIA part is 382 mm², while the Intel part's die size is unknown in the database.

Memory architecture is a major divider. The Intel Arc Pro B370 uses system-shared memory, meaning its memory size, type, and bus width are all listed as system-shared, with bandwidth being system-dependent. The NVIDIA N1 16SM uses 128 GB of LPDDR5X memory on a 256-bit bus, delivering 273.2 GB/s of bandwidth. The memory clock for the NVIDIA part is 1067 MHz with an effective data rate of 8.5 Gbps, while the Intel part's memory clock is system-shared.

The compute unit configurations differ significantly. The Intel part has 1280 shading units, 40 TMUs, 20 ROPs, and 10 RT cores. The NVIDIA part has 2048 shading units, 128 TMUs, 24 ROPs, and 16 RT cores. The NVIDIA part also includes 64 tensor cores, while the Intel part lists no tensor cores. FP16 throughput tells a story about architecture priorities: the Intel part achieves 12.29 TFLOPS with a 2:1 ratio, indicating it can do twice the FP16 work per cycle compared to FP32. The NVIDIA part achieves 9.609 TFLOPS FP16 with a 1:1 ratio, meaning it processes FP16 at the same rate as FP32.

The bus interface also differs. The Intel Arc Pro B370 uses an IGP bus interface with no power connectors, while the NVIDIA N1 16SM uses a PCIe 5.0 x16 interface, also with no power connectors. Display outputs differ as well: the Intel part lists portable device dependent outputs, while the NVIDIA part lists a single HDMI output. The NVIDIA part's die size of 382 mm² is notable for an integrated GPU, suggesting a large amount of on-die logic.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark results for these two parts. The wins count is 0 for both, and the head-to-head benchmarks array is empty. However, the recorded specifications allow for direct numerical comparisons that indicate performance relationships.

In FP32 compute, the NVIDIA N1 16SM delivers 9.609 TFLOPS, which is 56% higher than the Intel Arc Pro B370's 6.144 TFLOPS. The difference in texture rate is more pronounced: 300.3 GTexel/s versus 96.00 GTexel/s, a 213% advantage for NVIDIA. Pixel rate favors NVIDIA by 17%, at 56.30 GPixel/s versus 48.00 GPixel/s. These gaps reflect the NVIDIA part's larger shading unit count (2048 vs 1280) and TMU count (128 vs 40).

In FP16 compute, the relationship flips. The Intel Arc Pro B370 achieves 12.29 TFLOPS, which is 28% higher than the NVIDIA N1 16SM's 9.609 TFLOPS. This is a direct result of the Intel part's 2:1 FP16 ratio, which allows it to double its FP32 throughput when working with reduced precision. The NVIDIA part's 1:1 ratio means its FP16 performance equals its FP32 performance, so it loses the FP16 comparison despite having higher raw FP32 throughput.

Clock speeds show a mixed picture. The Intel part boosts to 2400 MHz, which is 2.3% higher than the NVIDIA part's 2346 MHz boost. However, the NVIDIA part has a much higher base clock at 741 MHz versus 300 MHz, a 147% advantage. The NVIDIA part also has a higher memory clock at 1067 MHz, while the Intel part's memory clock is system-shared.

Memory bandwidth is where the NVIDIA part dominates decisively. Its 273.2 GB/s is a fixed specification, while the Intel part's bandwidth is system dependent and cannot be quantified from the database. The NVIDIA part's 128 GB capacity and 256-bit bus width are also fixed, giving it a substantial advantage in any memory-bound workload.

Both parts are rated at the 50th percentile among all GPUs in the database, and both have an average benchmark score of 0, indicating no recorded benchmark runs. The Intel part's predecessor is HD Graphics-WM, while the NVIDIA part has no predecessor listed.

The Verdict

The data indicates that these two GPUs should not be considered direct competitors. The Intel Arc Pro B370 is a modern graphics solution for portable devices, supporting DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4. The NVIDIA N1 16SM is a compute-focused integrated part with no graphics API support, making it unsuitable for gaming or graphics applications that rely on those APIs.

For users who need graphics API compatibility, the Intel Arc Pro B370 is the only choice between the two. Its DirectX 12 Ultimate support enables modern game features, and its Vulkan 1.4 support covers cross-platform graphics workloads. Its 25 W TDP makes it suitable for power-constrained portable devices, and its 3 nm process node suggests efficient operation.

For users who need raw compute throughput and fixed memory resources, the NVIDIA N1 16SM is the stronger option. Its 9.609 TFLOPS FP32 performance, 300.3 GTexel/s texture rate, and 273.2 GB/s memory bandwidth are all significantly higher than the Intel part's corresponding values. Its 128 GB of LPDDR5X memory is a fixed resource that does not depend on system configuration, unlike the Intel part's system-shared memory.

The NVIDIA part also has more RT cores (16 vs 10) and 64 tensor cores, while the Intel part has no tensor cores. The NVIDIA part's PCIe 5.0 x16 interface provides a wider bus connection than the Intel part's IGP interface, though both are integrated solutions with no power connectors.

The FP16 comparison favors the Intel part at 12.29 TFLOPS versus 9.609 TFLOPS, which may matter for workloads that use reduced precision. However, the NVIDIA part's 1:1 FP16 ratio suggests it treats FP16 as a first-class citizen rather than a fast path, and its overall compute advantage in FP32 is substantial.

The release dates suggest the Intel part came first, with a January 2026 date versus May 2026 for the NVIDIA part. Both are listed as Active production status. The NVIDIA part's 382 mm² die size is large for an integrated GPU, while the Intel part's die size is unknown.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The NVIDIA N1 16SM delivers 9.609 TFLOPS FP32, which is 56% higher than the Intel Arc Pro B370's 6.144 TFLOPS.

Q: Does the NVIDIA N1 16SM support DirectX?

A: No. The database lists DirectX as N/A for the NVIDIA N1 16SM, while the Intel Arc Pro B370 supports DirectX 12 Ultimate (12_2).

Q: How much memory does each GPU have?

A: The NVIDIA N1 16SM has 128 GB of LPDDR5X memory on a 256-bit bus with 273.2 GB/s bandwidth. The Intel Arc Pro B370 uses system-shared memory with system-dependent bandwidth.

Q: Which GPU has more RT cores?

A: The NVIDIA N1 16SM has 16 RT cores, while the Intel Arc Pro B370 has 10 RT cores.

Q: What is the FP16 performance difference?

A: The Intel Arc Pro B370 achieves 12.29 TFLOPS FP16 with a 2:1 ratio, which is 28% higher than the NVIDIA N1 16SM's 9.609 TFLOPS FP16 with a 1:1 ratio.

Q: What process nodes do these GPUs use?

A: The Intel Arc Pro B370 uses a 3 nm node from Intel's foundry, while the NVIDIA N1 16SM uses a 5 nm node from TSMC.

Specification Differences

| Specification | Intel Arc Pro B370 | NVIDIA N1 16SM |

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

| Architecture | Xe3-LPG | Blackwell 2.0 |

| Process Node | 3 nm | 5 nm |

| Foundry | Intel | TSMC |

| Die Size | Unknown | 382 mm² |

| Base Clock | 300 MHz | 741 MHz |

| Boost Clock | 2400 MHz | 2346 MHz |

| Memory Size | System Shared | 128 GB |

| Memory Type | System Shared | LPDDR5X |

| Memory Bus Width | System Shared | 256 bit |

| Memory Bandwidth | System Dependent | 273.2 GB/s |

| Memory Clock | System Shared | 1067 MHz 8.5 Gbps effective |

| Shading Units | 1280 | 2048 |

| TMUs | 40 | 128 |

| ROPs | 20 | 24 |

| RT Cores | 10 | 16 |

| Tensor Cores | None listed | 64 |

| Pixel Rate | 48.00 GPixel/s | 56.30 GPixel/s |

| Texture Rate | 96.00 GTexel/s | 300.3 GTexel/s |

| FP32 | 6.144 TFLOPS | 9.609 TFLOPS |

| FP16 | 12.29 TFLOPS (2:1) | 9.609 TFLOPS (1:1) |

| TDP | 25 W | Unknown |

| Bus Interface | IGP | 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 | 2026-01-26 | 2026-05-31 |

| Predecessor | HD Graphics-WM | None listed |