Intel Arc A580 vs NVIDIA GeForce RTX 5090 Mobile Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive sweep in the direct comparisons between the Intel Arc A580 and the NVIDIA GeForce RTX 5090 Mobile. Across all three shared benchmark tests, the NVIDIA part finishes ahead, with the Intel card trailing by margins ranging from roughly 55% to 62%. The largest gap appears in the 3DMark Steel Nomad DX12 test, where the RTX 5090 Mobile scores 5871 against the Arc A580's 2229, a delta of -62%. This indicates that in modern DirectX 12 workloads, the NVIDIA solution delivers more than two and a half times the performance of the Intel part.

The compute-oriented results tell a similar story. In Geekbench OpenCL, the RTX 5090 Mobile records 201834 points, while the Arc A580 manages 91657, a -54.6% delta. The Vulkan test shows a -60% gap, with scores of 198405 and 79381 respectively. The consistency of these margins across different APIs suggests that the performance advantage is not workload-specific but rather a fundamental throughput difference. The NVIDIA card wins all three head-to-head tests, giving it a 3-0 record in this comparison.

When placed against their respective peer groups, both cards occupy similar percentile positions. The Arc A580 sits at the 87th percentile among all GPUs, while the RTX 5090 Mobile is at the 84th percentile. The Intel card's nearest rivals include the AMD Radeon RX 5600 OEM (0.6% faster), the Intel Arc A570M (0.8% faster), the AMD Radeon RX 9070 GRE (0.7% slower), and the AMD Radeon RX 6950 XT (1.1% slower). The NVIDIA mobile part's closest competitors are the AMD Radeon Pro 5500 XT (0.5% faster), the Intel Arc A730M (1% faster), and the NVIDIA RTX 5880 Ada Generation (1.8% faster). Notably, the RTX 5090 Mobile averages 45152 across all its recorded benchmarks, while the Arc A580 averages 57756, meaning the Intel card actually has a higher overall average despite losing every direct comparison. This occurs because the NVIDIA part's benchmark suite includes several lower-scoring PassMark tests that drag its average down.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. Intel's Arc A580 uses the DG2-512 chip built on the Xe-HPG architecture, belonging to the Alchemist generation (Arc 5). It is fabricated on a 6 nm process at TSMC, with 21,700 million transistors spread across a 406 mm² die, yielding a transistor density of 53.4 million per square millimeter. The NVIDIA GeForce RTX 5090 Mobile employs the GB203 chip with the Blackwell 2.0 architecture, part of the GeForce 50 Mobile generation. It uses a 5 nm TSMC process, packs 45,600 million transistors into a smaller 378 mm² die, and achieves a much higher density of 120.6 million per square millimeter.

The compute resources differ substantially. The Arc A580 has 3072 shading units, 192 texture mapping units, and 96 raster output units. It includes 24 ray tracing cores but no dedicated tensor cores. The RTX 5090 Mobile, by contrast, fields 10496 shading units, 328 TMUs, and 112 ROPs. It carries 82 ray tracing cores and 328 tensor cores. These numbers translate directly into raw throughput figures: the Intel card delivers 12.29 TFLOPS FP32 and 24.58 TFLOPS FP16 (2:1 ratio), while the NVIDIA part reaches 31.80 TFLOPS for both FP32 and FP16 (1:1 ratio).

Memory configurations also diverge sharply. The Arc A580 comes with 8 GB of GDDR6 on a 256-bit bus, running at 2000 MHz (16 Gbps effective), producing 512.0 GB/s of bandwidth. The RTX 5090 Mobile offers 24 GB of GDDR7 on the same 256-bit bus width, but at 1750 MHz (28 Gbps effective), achieving 896.0 GB/s. The NVIDIA part has nearly double the memory bandwidth and three times the capacity. Pixel and texture rates follow suit: the Arc A580 reaches 192.0 GPixel/s and 384.0 GTexel/s, whereas the RTX 5090 Mobile posts 169.7 GPixel/s and 496.9 GTexel/s. The Intel card actually leads in pixel fill rate, but the NVIDIA part wins texture throughput.

Power and physical specifications reveal a major design split. The Arc A580 is a dual-slot desktop card with a 175 W TDP, requiring two 8-pin power connectors and a 450 W suggested power supply. It connects via PCIe 4.0 x16 and offers 1x HDMI 2.1 plus 3x DisplayPort 2.0 outputs. The RTX 5090 Mobile is an integrated graphics processor (IGP) with a 95 W TDP, no power connectors, and a PCIe 5.0 x16 interface. Its display outputs are portable device dependent. The NVIDIA chip uses roughly half the power while delivering far higher performance, reflecting the efficiency gains of the newer 5 nm process and denser transistor layout.

Where Each One Wins

Based on the recorded benchmarks, the RTX 5090 Mobile wins in every measured category. In 3DMark Steel Nomad DX12, it outperforms the Arc A580 by 62%, making it the clear choice for modern DirectX 12 gaming workloads. In Geekbench OpenCL and Vulkan, it leads by 54.6% and 60% respectively, indicating strong compute performance across both general-purpose and graphics APIs. The NVIDIA part's additional tensor cores and higher FP32 throughput suggest it would handle AI-accelerated tasks and heavy compute workloads more effectively, though no specific AI benchmarks are present in the data.

The Arc A580 does have some areas where it is not entirely outclassed. Its pixel rate of 192.0 GPixel/s exceeds the RTX 5090 Mobile's 169.7 GPixel/s, which could translate to an advantage in fill-rate-bound scenarios at lower resolutions. Its higher average benchmark score (57756 vs 45152) indicates that when considering all recorded tests, including the PassMark suite where the NVIDIA part scores relatively low (for example, 138 in PassMark DirectX 12 and 183 in DirectX 10), the Intel card maintains a more consistent overall profile. However, these PassMark scores are not part of the head-to-head comparison and may reflect different test conditions or driver optimizations.

For use cases, the RTX 5090 Mobile is the superior choice for high-end gaming, particularly at higher resolutions or with ray tracing enabled, given its 62% lead in the DX12 test and its 82 dedicated ray tracing cores. It also suits professional compute workloads that can leverage its 328 tensor cores and 31.80 TFLOPS of FP32 throughput. The Arc A580, with its lower power draw relative to its desktop form factor and its competitive average score, could be adequate for 1080p gaming or general compute tasks where the NVIDIA part's extra capacity is unnecessary. Its 8 GB memory may limit very large workloads, but for typical use it remains functional.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The Intel Arc A580 has a higher average benchmark score of 57756, compared to the NVIDIA GeForce RTX 5090 Mobile's 45152.

Q: How large is the performance gap in the 3DMark Steel Nomad DX12 test?

A: The RTX 5090 Mobile scores 5871, while the Arc A580 scores 2229, a delta of -62% in favor of the NVIDIA card.

Q: What are the memory capacities of the two cards?

A: The Arc A580 has 8 GB of GDDR6 memory, while the RTX 5090 Mobile has 24 GB of GDDR7 memory.

Q: Which GPU has more shading units?

A: The RTX 5090 Mobile has 10496 shading units, while the Arc A580 has 3072 shading units.

Q: What is the TDP of each GPU?

A: The Arc A580 has a TDP of 175 W, whereas the RTX 5090 Mobile has a TDP of 95 W.

Q: Which card has a higher pixel fill rate?

A: The Arc A580 has a pixel rate of 192.0 GPixel/s, which is higher than the RTX 5090 Mobile's 169.7 GPixel/s.

The Verdict

The data points to a clear winner for most applications. The NVIDIA GeForce RTX 5090 Mobile outperforms the Intel Arc A580 by significant margins in every head-to-head benchmark, with deltas of -54.6%, -60%, and -62%. Its 24 GB of GDDR7 memory, 10496 shading units, 82 ray tracing cores, and 328 tensor cores make it the more capable hardware for demanding gaming and compute tasks. The 31.80 TFLOPS FP32 throughput is more than double the Arc A580's 12.29 TFLOPS, and its 896.0 GB/s memory bandwidth far exceeds the Intel card's 512.0 GB/s.

However, the Arc A580 is not without merit. It holds a higher average benchmark score (57756 vs 45152), a superior pixel rate, and a lower TDP relative to its desktop power requirements. For users who prioritize fill-rate-bound scenarios or who need a card that performs consistently across a broader range of tests, the Intel part could be sufficient. Yet the RTX 5090 Mobile's dominance in the direct comparisons, combined with its newer architecture and higher transistor density, makes it the stronger overall product. The Arc A580 might be chosen for specific niche uses, but the recorded benchmarks show that the RTX 5090 Mobile is the superior GPU in nearly every measurable way.

Specification Differences

| Specification | Intel Arc A580 | NVIDIA GeForce RTX 5090 Mobile |

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

| Architecture | Xe-HPG | Blackwell 2.0 |

| Generation | Alchemist (Arc 5) | GeForce 50 Mobile |

| Process Node | 6 nm | 5 nm |

| Transistors | 21,700 million | 45,600 million |

| Die Size | 406 mm² | 378 mm² |

| Transistor Density | 53.4M / mm² | 120.6M / mm² |

| Base Clock | 1700 MHz | 990 MHz |

| Boost Clock | 2000 MHz | 1515 MHz |

| Memory Clock | 2000 MHz (16 Gbps effective) | 1750 MHz (28 Gbps effective) |

| Memory Size | 8 GB | 24 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Bus | 256 bit | 256 bit |

| Memory Bandwidth | 512.0 GB/s | 896.0 GB/s |

| Shading Units | 3072 | 10496 |

| TMUs | 192 | 328 |

| ROPs | 96 | 112 |

| Ray Tracing Cores | 24 | 82 |

| Tensor Cores | None | 328 |

| Pixel Rate | 192.0 GPixel/s | 169.7 GPixel/s |

| Texture Rate | 384.0 GTexel/s | 496.9 GTexel/s |

| FP32 Performance | 12.29 TFLOPS | 31.80 TFLOPS |

| FP16 Performance | 24.58 TFLOPS (2:1) | 31.80 TFLOPS (1:1) |

| TDP | 175 W | 95 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 2x 8-pin | None |

| Suggested PSU | 450 W | None |

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

| Display Outputs | 1x HDMI 2.1, 3x DisplayPort 2.0 | Portable Device Dependent |

| Release Date | 2023-10-09 | 2025-03-26 |

| Predecessor | Xe Graphics | GeForce 40 Mobile |

| Successor | Battlemage | None |