Intel Arc Pro B65 vs NVIDIA GeForce RTX 4060 Mobile Comparison

Intel’s Arc Pro B65 and NVIDIA’s GeForce RTX 4060 Mobile occupy different corners of the graphics hardware space: one is a power-hungry workstation-oriented card with a massive memory pool, the other is a mobile GPU built for efficiency inside laptops. The recorded data shows a clear split between raw throughput and practical portability.

FAQ

Q: Which GPU has more memory and bandwidth?

A: The Intel Arc Pro B65 ships with 32 GB of GDDR6 on a 256-bit bus, delivering 608.0 GB/s of memory bandwidth. The NVIDIA GeForce RTX 4060 Mobile offers 8 GB of GDDR6 on a 128-bit bus, with 256.0 GB/s of bandwidth.

Q: How do their FP32 compute performances compare?

A: The Intel card reaches 12.29 TFLOPS in FP32, while the NVIDIA mobile GPU reaches 11.61 TFLOPS. The Intel part holds a roughly 6% lead in raw single-precision throughput.

Q: Which GPU uses more power?

A: The Intel Arc Pro B65 has a TDP of 200 W and requires a 550 W power supply with a single 8-pin connector. The NVIDIA GeForce RTX 4060 Mobile has a TDP of 115 W and uses no external power connectors, being designed as an integrated graphics package for laptops.

Q: What is the difference in transistor density?

A: The NVIDIA chip, AD107, packs 18,900 million transistors into a 159 mm² die, yielding a density of 118.9M / mm². The Intel BMG-G21 die is 272 mm² with 19,600 million transistors, resulting in 72.1M / mm².

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

A: The NVIDIA GeForce RTX 4060 Mobile has 3072 shading units and 24 ray tracing cores. The Intel Arc Pro B65 has 2560 shading units and 20 ray tracing cores.

Q: What benchmark scores exist for these GPUs?

A: The database contains benchmark results only for the NVIDIA GeForce RTX 4060 Mobile. Its average benchmark score is 22729, with a percentile rank of 67 among all GPUs. The Intel Arc Pro B65 has no recorded benchmarks and a percentile rank of 50.

Architecture Differences

The two GPUs come from different architectural families. Intel uses Xe2-HPG, the Battlemage generation for its Pro Series, built on a 5 nm process at TSMC. NVIDIA uses Ada Lovelace, its GeForce 40-series mobile architecture, also on a 5 nm process at TSMC. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API feature parity is complete.

The physical designs diverge significantly. Intel’s BMG-G21 die measures 272 mm² and contains 19,600 million transistors, with a transistor density of 72.1M / mm². NVIDIA’s AD107 die is much smaller at 159 mm², holding 18,900 million transistors at a higher density of 118.9M / mm². The density difference indicates NVIDIA packs more transistors per area, while Intel uses a larger die to accommodate its 32 GB memory subsystem.

Memory architecture separates these parts further. The Intel card uses a 256-bit bus with 608.0 GB/s of bandwidth, a figure more than double the NVIDIA’s 256.0 GB/s over a 128-bit bus. Clock speeds also differ: Intel runs at a flat 2400 MHz for both base and boost, while NVIDIA scales from 1545 MHz base to 1890 MHz boost. Intel’s memory clock is 2375 MHz (19 Gbps effective), versus NVIDIA’s 2000 MHz (16 Gbps effective).

Compute resource allocation varies. Intel fields 2560 shading units, 160 texture mapping units, and 80 raster output units. NVIDIA counters with 3072 shading units, 96 TMUs, and 48 ROPs. NVIDIA also includes 96 tensor cores, a feature Intel’s card does not list. Pixel rate favors Intel at 192.0 GPixel/s versus 90.72 GPixel/s for NVIDIA. Texture rate likewise favors Intel at 384.0 GTexel/s versus 181.4 GTexel/s.

The Intel card is a dual-slot, PCIe 5.0 x16 device with four DisplayPort 2.1 outputs. The NVIDIA part is an IGP (integrated graphics package) with a PCIe 4.0 x8 interface and display outputs described as portable device dependent. Power delivery differs: Intel needs a 200 W TDP with a 550 W suggested power supply and one 8-pin connector; NVIDIA runs at 115 W with no external power connectors.

Where Each One Wins

The Intel Arc Pro B65 wins in scenarios demanding massive memory capacity and high bandwidth. Its 32 GB VRAM and 608.0 GB/s bandwidth suit workloads like large dataset processing, high-resolution texture streaming, or compute tasks that exceed the 8 GB frame buffer of the NVIDIA part. The higher pixel rate (192.0 GPixel/s) and texture rate (384.0 GTexel/s) also give Intel an edge in fill-rate-bound rendering.

The NVIDIA GeForce RTX 4060 Mobile wins in efficiency and portability. Its 115 W TDP versus 200 W makes it suitable for laptops, and its IGP form factor with no power connectors reflects that design target. The higher shading unit count (3072 versus 2560) and presence of tensor cores give NVIDIA an advantage in shader-heavy and AI-accelerated workloads. Its 96 tensor cores are not present on the Intel card at all.

Benchmark data only exists for NVIDIA, so measured wins favor it by default. The RTX 4060 Mobile’s average benchmark score of 22729 sits at the 67th percentile of all GPUs. Its nearest rivals in the database include the NVIDIA GeForce RTX 2080 with an average score of 22895 (0.7% higher), the Intel Arc B580 at 23021 (1.3% higher), the AMD Radeon RX 7700 XT at 22549 (0.8% lower), and the NVIDIA GeForce RTX 5060 Mobile at 22435 (1.3% lower). This places the mobile card in a tight performance cluster with desktop parts from the previous generation.

Specification Differences

| Specification | Intel Arc Pro B65 | NVIDIA GeForce RTX 4060 Mobile |

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

| Architecture | Xe2-HPG | Ada Lovelace |

| Generation | Battlemage (Pro Series) | GeForce 40 Mobile |

| Process Node | 5 nm | 5 nm |

| Transistors | 19,600 million | 18,900 million |

| Die Size | 272 mm² | 159 mm² |

| Transistor Density | 72.1M / mm² | 118.9M / mm² |

| Base Clock | 2400 MHz | 1545 MHz |

| Boost Clock | 2400 MHz | 1890 MHz |

| Memory Size | 32 GB | 8 GB |

| Memory Type | GDDR6 | GDDR6 |

| Memory Bus | 256 bit | 128 bit |

| Memory Bandwidth | 608.0 GB/s | 256.0 GB/s |

| Shading Units | 2560 | 3072 |

| TMUs | 160 | 96 |

| ROPs | 80 | 48 |

| Ray Tracing Cores | 20 | 24 |

| Tensor Cores | None | 96 |

| Pixel Rate | 192.0 GPixel/s | 90.72 GPixel/s |

| Texture Rate | 384.0 GTexel/s | 181.4 GTexel/s |

| FP32 | 12.29 TFLOPS | 11.61 TFLOPS |

| FP16 | 24.58 TFLOPS (2:1) | 11.61 TFLOPS (1:1) |

| TDP | 200 W | 115 W |

| Slot Width | Dual-slot | IGP |

| Power Connectors | 1x 8-pin | None |

| Suggested PSU | 550 W | None |

| Bus Interface | PCIe 5.0 x16 | PCIe 4.0 x8 |

| Display Outputs | 4x DisplayPort 2.1 | Portable Device Dependent |

| Release Date | 2026-03-31 | 2023-01-02 |

Head-to-Head Benchmarks

The database has no direct head-to-head benchmark results between these two GPUs. All measured scores belong to the NVIDIA GeForce RTX 4060 Mobile. Its Geekbench OpenCL score is 89420, and its Geekbench Vulkan score is 89569. Passmark results include DirectX 10 at 107, DirectX 11 at 157, DirectX 12 at 73, DirectX 9 at 216, G2D at 730, G3D at 17469, and GPU compute at 6816.

Without a direct comparison, the nearest rivals for NVIDIA provide context. The RTX 4060 Mobile’s average score of 22729 is nearly identical to the RTX 2080’s 22895, a 0.7% deficit. It also trails the Intel Arc B580 by 1.3% (23021 average) but beats the AMD Radeon RX 7700 XT by 0.8% (22549 average) and the RTX 5060 Mobile by 1.3% (22435 average). These deltas indicate the mobile GPU performs at desktop-class levels from two generations ago.

The Intel Arc Pro B65’s absence from the benchmark suite means its performance can only be inferred from theoretical specifications. Its FP32 throughput of 12.29 TFLOPS edges out NVIDIA’s 11.61 TFLOPS by about 5.9%. The FP16 comparison is far more lopsided: Intel reaches 24.58 TFLOPS at a 2:1 ratio, while NVIDIA’s FP16 is 11.61 TFLOPS at a 1:1 ratio. This gives Intel a 2.1x advantage in half-precision compute, relevant for AI inference and certain scientific workloads.

The Verdict

The data points to distinct roles. The Intel Arc Pro B65 is built for stationary, high-capacity workloads. Its 32 GB memory, 608.0 GB/s bandwidth, and 200 W TDP indicate a card meant for professional rendering, large-scale compute, and multi-display setups with four DisplayPort 2.1 outputs. The 2.1x FP16 advantage over NVIDIA further supports compute-heavy use cases.

The NVIDIA GeForce RTX 4060 Mobile is a mobile part through and through. Its 115 W TDP, IGP form factor, and lack of power connectors make it suitable for laptops. The benchmark data confirms its capability: an average score of 22729 at the 67th percentile, with performance within 1.3% of desktop GPUs like the RTX 2080 and Arc B580. The 96 tensor cores give it a feature Intel lacks.

Users who need maximum VRAM and bandwidth, and who can supply 200 W of power, should select the Intel Arc Pro B65. Users who need desktop-class performance in a mobile chassis, with tensor core acceleration and lower power draw, should select the NVIDIA GeForce RTX 4060 Mobile. The recorded measurements only validate NVIDIA’s real-world performance; Intel’s card remains a specification-driven option with no benchmark data in the database.