Intel Arc A350M vs NVIDIA GeForce GTX 1060 6 GB Comparison

FAQ

Q: How does the Intel Arc A350M compare to the NVIDIA GeForce GTX 1060 6 GB in OpenCL performance?

A: The GTX 1060 6 GB scores 32322 in Geekbench OpenCL, while the Arc A350M scores 24546. This gives the NVIDIA card a 24.1% lead in that workload.

Q: Which GPU wins in Vulkan performance?

A: The Arc A350M takes the Vulkan test with a score of 24747 versus the GTX 1060's 18659, a 32.6% advantage for the Intel part.

Q: What is the architectural generation gap between these two?

A: The Arc A350M uses Intel's Xe-HPG architecture on a 6 nm TSMC process, while the GTX 1060 uses NVIDIA's Pascal architecture on a 16 nm TSMC process. The Arc chip is Alchemist generation, while the GTX 1060 is GeForce 10-series.

Q: How do their memory subsystems differ?

A: The Arc A350M has 4 GB of GDDR6 on a 64-bit bus with 112.0 GB/s bandwidth. The GTX 1060 has 6 GB of GDDR5 on a 192-bit bus with 192.2 GB/s bandwidth.

Q: Which GPU has a higher transistor density?

A: The Arc A350M packs 7,200 million transistors into a 157 mm² die, yielding 45.9 million transistors per mm². The GTX 1060 has 4,400 million transistors on a 200 mm² die, for 22.0 million per mm².

Q: What are the average benchmark scores and percentile rankings?

A: The Arc A350M averages 24647 across recorded tests and sits at the 70th percentile of all GPUs. The GTX 1060 averages 21856 and sits at the 67th percentile.

Where Each One Wins

The recorded head-to-head data splits cleanly: one win per GPU. The GTX 1060 6 GB dominates in OpenCL compute workloads, scoring 32322 versus 24546 for the Arc A350M. That 24.1% margin indicates the NVIDIA part sustains higher raw throughput in general-purpose compute tasks, likely due to its larger shading unit count (1280 versus 768) and higher FP32 rate (4.375 TFLOPS versus 3.379 TFLOPS). For users running OpenCL-based applications, rendering pipelines, or scientific workloads, the GTX 1060 is the stronger choice.

Conversely, the Arc A350M wins decisively in Vulkan, posting 24747 against 18659, a 32.6% advantage. This suggests the Intel architecture's modern feature set and driver optimizations for Vulkan give it a clear edge in current-generation game APIs and Vulkan-native applications. The Arc also benefits from DirectX 12 Ultimate (12_2) support, while the GTX 1060 is limited to DirectX 12 (12_1), which matters for newer titles leveraging mesh shaders or ray tracing features.

For overall versatility, the Arc A350M's average benchmark score of 24647 exceeds the GTX 1060's 21856 by roughly 12.8%, despite losing the OpenCL test. The Vulkan win carries more weight in the aggregate, and the Arc's higher percentile rank (70th versus 67th) confirms it places better against the full GPU landscape. However, the GTX 1060 remains competitive in compute-heavy scenarios, and its 6 GB frame buffer versus 4 GB gives it more headroom for texture-heavy workloads or large datasets.

Architecture Differences

The Arc A350M is built on Intel's Xe-HPG architecture, specifically the DG2-128 chip, fabricated at TSMC on a 6 nm process. It integrates 7,200 million transistors on a 157 mm² die, achieving a density of 45.9 million transistors per mm². The GTX 1060 uses NVIDIA's Pascal architecture with the GP106 chip, also from TSMC but on a 16 nm process, containing 4,400 million transistors across a 200 mm² die, for 22.0 million per mm². The Arc's newer process node allows over twice the transistor density.

Memory technology diverges sharply. The Arc uses GDDR6 with an effective data rate of 14 Gbps, while the GTX 1060 uses GDDR5 at 8 Gbps effective. The GTX 1060 compensates with a wider 192-bit bus versus the Arc's 64-bit bus, giving it 192.2 GB/s bandwidth against the Arc's 112.0 GB/s. The GTX 1060 also carries 6 GB of VRAM versus 4 GB.

Compute feature support differs: the Arc supports DirectX 12 Ultimate (12_2), which includes hardware ray tracing via its 6 RT cores, while the GTX 1060 only reaches DirectX 12 (12_1) with no RT cores. Both support OpenGL 4.6 and Vulkan 1.4. The Arc's FP16 throughput is 6.758 TFLOPS (2:1 ratio), while the GTX 1060's FP16 is severely limited at 68.36 GFLOPS (1:64 ratio), making the Intel part substantially better for mixed-precision workloads. The GTX 1060 does offer higher peak FP32 (4.375 TFLOPS versus 3.379 TFLOPS), higher pixel rate (82.03 GPixel/s versus 52.80 GPixel/s), and higher texture rate (136.7 GTexel/s versus 105.6 GTexel/s).

Specification Differences

| Specification | Intel Arc A350M | NVIDIA GeForce GTX 1060 6 GB |

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

| Architecture | Xe-HPG | Pascal |

| Process node | 6 nm | 16 nm |

| Transistors | 7,200 million | 4,400 million |

| Die size | 157 mm² | 200 mm² |

| Base clock | 1150 MHz | 1506 MHz |

| Boost clock | 2200 MHz | 1709 MHz |

| Memory size | 4 GB | 6 GB |

| Memory type | GDDR6 | GDDR5 |

| Memory bus width | 64 bit | 192 bit |

| Memory bandwidth | 112.0 GB/s | 192.2 GB/s |

| Shading units | 768 | 1280 |

| TMUs | 48 | 80 |

| ROPs | 24 | 48 |

| RT cores | 6 | None |

| Pixel rate | 52.80 GPixel/s | 82.03 GPixel/s |

| Texture rate | 105.6 GTexel/s | 136.7 GTexel/s |

| FP32 | 3.379 TFLOPS | 4.375 TFLOPS |

| FP16 | 6.758 TFLOPS (2:1) | 68.36 GFLOPS (1:64) |

| TDP | 25 W | 120 W |

| Slot width | IGP | Dual-slot |

| Power connectors | None | 1x 6-pin |

| Bus interface | PCIe 4.0 x8 | PCIe 3.0 x16 |

| DirectX | 12 Ultimate (12_2) | 12 (12_1) |

The GTX 1060 is a desktop card with a 250 mm length and 111 mm height, requiring a 300 W suggested PSU. The Arc A350M is an integrated graphics processor (IGP) for mobile devices, so its display outputs are portable device dependent, and it draws only 25 W. The GTX 1060 offers discrete display outputs including 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a.

Head-to-Head Benchmarks

The two recorded head-to-head tests show a clear split, with each GPU winning one discipline. In Geekbench OpenCL, the GTX 1060 6 GB scores 32322, while the Arc A350M scores 24546. The delta of -24.1% means the Arc trails by nearly a quarter in this test. This result aligns with the GTX 1060's higher shader count (1280 versus 768) and higher FP32 throughput (4.375 TFLOPS versus 3.379 TFLOPS). OpenCL workloads that scale with raw compute units and memory bandwidth favor the NVIDIA card, which also has 192.2 GB/s versus the Arc's 112.0 GB/s.

In Geekbench Vulkan, the situation reverses. The Arc A350M scores 24747, and the GTX 1060 scores 18659, giving the Intel part a 32.6% lead. This is a substantial margin, indicating that the Arc's newer architecture, with its 6 RT cores and DirectX 12 Ultimate feature set, translates into superior Vulkan API utilization. The GTX 1060's Pascal architecture predates many modern Vulkan extensions, and its 1:64 FP16 ratio (68.36 GFLOPS versus 6.758 TFLOPS for the Arc) may hamper certain compute paths.

Across both tests, the Arc A350M's average score is 24647, compared to the GTX 1060's 21856. That is a 12.8% higher average for the Intel part. The Arc also ranks at the 70th percentile of all GPUs, versus the GTX 1060's 67th percentile. However, the GTX 1060's nearest rivals include the AMD Radeon RX 6700S (average 22154, delta -1.3%) and the AMD Radeon RX 5700 (average 22170, delta -1.4%), meaning the NVIDIA card sits slightly below those in the aggregate. The Arc A350M's nearest rivals include the AMD Radeon RX 590 (average 24744, delta -0.4%) and the NVIDIA RTX A5000 Mobile (average 24763, delta -0.5%), placing the Intel part in a higher performance tier overall.

The GTX 1060's OpenCL win is its strongest showing, but the Vulkan loss is decisive. For users prioritizing Vulkan-based gaming or modern API features, the Arc A350M is the better choice despite its smaller VRAM and lower raw compute. For compute-heavy OpenCL tasks, the GTX 1060 retains a meaningful edge. The data also shows the Arc's FP16 capability (6.758 TFLOPS) dwarfs the GTX 1060's (68.36 GFLOPS), which could matter in AI inference or media processing that uses reduced precision. The GTX 1060's 6 GB VRAM and higher bandwidth remain advantages for large textures or memory-intensive workloads, but the Arc's architectural modernity gives it the overall benchmark edge.