Intel Arc Graphics 112EU Mobile vs Intel Arc Pro B65 Comparison

The Verdict

The data places these two Intel GPUs at opposite ends of the mobile-to-pro workstation spectrum. The Intel Arc Graphics 112EU Mobile is an integrated graphics processor built for thin-and-light portables, while the Intel Arc Pro B65 is a dual-slot, 200 W discrete workstation card with 32 GB of dedicated GDDR6 memory. The recorded specifications show no overlap in physical design, memory architecture, or performance class.

For users constrained to a laptop with no expansion slots, the Arc Graphics 112EU Mobile is the only option, as it is an IGP with a Ring Bus interface. For anyone building or upgrading a desktop workstation that requires large-frame buffer rendering, ray tracing, or PCIe 5.0 connectivity, the Arc Pro B65 is the clear choice based on every measurable compute and memory metric. The B65 delivers roughly 3.1 times the FP32 throughput, 3.7 times the texture fill rate, and 3.6 times the pixel fill rate of the 112EU Mobile. The verdict is straightforward: the 112EU Mobile serves integrated graphics duty in Meteor Lake laptops, the B65 serves professional desktop workloads.

Architecture Differences

The two chips come from different Intel graphics lineages. The Arc Graphics 112EU Mobile is based on the Xe-LPG architecture on the Meteor Lake chip, manufactured on Intel's 10 nm process node. It belongs to the Arc Graphics-M generation tied to Meteor Lake. The Arc Pro B65 uses the Xe2-HPG architecture on the BMG-G21 chip, part of the Battlemage Pro Series, fabricated by TSMC on a 5 nm process.

The B65's physical size is recorded at 272 mm² with 19,600 million transistors, yielding a transistor density of 72.1 million per mm². The 112EU Mobile has no recorded die size or transistor count in the database, so those figures cannot be compared directly.

Compute resources differ sharply. The 112EU Mobile packs 896 shading units, 56 texture mapping units, and 24 ROPs. The B65 has 2,560 shading units, 160 TMUs, and 80 ROPs. The B65 also includes 20 dedicated ray tracing cores; the 112EU Mobile records no RT core count. Neither part lists tensor cores.

Clock behavior also diverges. The 112EU Mobile runs a 300 MHz base clock and a 2200 MHz boost clock. The B65 runs a fixed 2400 MHz for both base and boost, with memory clocked at 2375 MHz (19 Gbps effective). The 112EU Mobile uses system-shared memory with system-dependent bandwidth, while the B65 has its own 32 GB GDDR6 pool on a 256-bit bus delivering 608.0 GB/s.

API support shows a functional gap. Both support OpenGL 4.6 and Vulkan 1.4. The 112EU Mobile supports DirectX 12 (12_1), while the B65 supports DirectX 12 Ultimate (12_2), which includes the full ray tracing feature set.

FAQ

Q: Which GPU has more shading units?

A: The Intel Arc Pro B65 has 2,560 shading units. The Intel Arc Graphics 112EU Mobile has 896 shading units.

Q: What is the memory configuration difference?

A: The 112EU Mobile uses system-shared memory with system-dependent bandwidth. The Arc Pro B65 has 32 GB of GDDR6 memory on a 256-bit bus with 608.0 GB/s bandwidth.

Q: Does the Arc Pro B65 support ray tracing?

A: Yes. The B65 has 20 ray tracing cores. The Arc Graphics 112EU Mobile has no recorded ray tracing core count.

Q: What are the power requirements for each?

A: The 112EU Mobile has a 65 W TDP and requires no power connectors as an IGP. The Arc Pro B65 has a 200 W TDP, requires one 8-pin power connector, and the database lists a suggested PSU of 550 W.

Q: When were these GPUs released?

A: The Arc Graphics 112EU Mobile has a release date of December 13, 2023. The Arc Pro B65 has a release date of March 31, 2026.

Q: Which GPU supports PCIe 5.0?

A: The Arc Pro B65 uses a PCIe 5.0 x16 bus interface. The 112EU Mobile uses a Ring Bus interface, as expected for an integrated processor.

Specification Differences

| Specification | Intel Arc Graphics 112EU Mobile | Intel Arc Pro B65 |

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

| Architecture | Xe-LPG | Xe2-HPG |

| Chip | Meteor Lake | BMG-G21 |

| Generation | Arc Graphics-M (Meteor Lake) | Battlemage (Pro Series) |

| Process Node | 10 nm (Intel) | 5 nm (TSMC) |

| Transistors | Not recorded | 19,600 million |

| Die Size | Not recorded | 272 mm² |

| Base Clock | 300 MHz | 2400 MHz |

| Boost Clock | 2200 MHz | 2400 MHz |

| Memory Size | System Shared | 32 GB |

| Memory Type | System Shared | GDDR6 |

| Memory Bus | System Shared | 256 bit |

| Memory Bandwidth | System Dependent | 608.0 GB/s |

| Shading Units | 896 | 2560 |

| TMUs | 56 | 160 |

| ROPs | 24 | 80 |

| Ray Tracing Cores | Not recorded | 20 |

| Pixel Rate | 52.80 GPixel/s | 192.0 GPixel/s |

| Texture Rate | 123.2 GTexel/s | 384.0 GTexel/s |

| FP32 Performance | 3.942 TFLOPS | 12.29 TFLOPS |

| FP16 Performance | 7.885 TFLOPS | 24.58 TFLOPS |

| TDP | 65 W | 200 W |

| Slot Width | IGP | Dual-slot |

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

| Suggested PSU | None | 550 W |

| Bus Interface | Ring Bus | PCIe 5.0 x16 |

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

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

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark runs between these two GPUs. However, the recorded theoretical peak rates allow a direct comparison of raw throughput limits.

The most decisive gap is in FP32 compute. The Arc Pro B65 reaches 12.29 TFLOPS, which is 3.1 times the 3.942 TFLOPS of the Arc Graphics 112EU Mobile. This indicates the B65 can process roughly three times as many single-precision floating-point operations per second, a critical factor for rendering, simulation, and compute workloads.

Texture fill rate shows a similar margin. The B65 delivers 384.0 GTexel/s versus 123.2 GTexel/s for the 112EU Mobile, a 3.1 times advantage. This means the B65 can apply textures to surfaces over three times faster, directly impacting geometry-heavy scenes.

Pixel fill rate favors the B65 at 192.0 GPixel/s versus 52.80 GPixel/s, a 3.6 times advantage. This translates to higher resolution output and more complex fragment shading per frame.

Memory bandwidth is the largest single-metric discrepancy. The B65's 608.0 GB/s dedicated bandwidth is not directly comparable to the 112EU Mobile's system-dependent shared memory, but the B65's figure is an order of magnitude beyond typical integrated memory sharing. This bandwidth supports the B65's 32 GB frame buffer for large datasets.

FP16 throughput also scales with the same 2:1 ratio on both parts. The B65 reaches 24.58 TFLOPS versus 7.885 TFLOPS for the 112EU Mobile, again a 3.1 times difference.

The B65's ray tracing cores add a capability the 112EU Mobile simply does not record, so any DirectX 12 Ultimate workload with hardware-accelerated ray tracing is exclusive to the B65.

Where Each One Wins

The Arc Graphics 112EU Mobile wins in the integrated graphics domain. Its 65 W TDP, IGP slot width, Ring Bus interface, and system-shared memory make it suitable for Meteor Lake laptops where no discrete GPU can be installed. It supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, which covers mainstream gaming and general graphics acceleration on portable devices. Its display outputs are portable-device dependent, meaning the laptop manufacturer decides the physical ports.

The Arc Pro B65 wins in every recorded performance metric and in professional feature support. Its 200 W TDP and dual-slot design indicate a desktop workstation card. The 32 GB GDDR6 memory with 608.0 GB/s bandwidth supports large models, high-resolution textures, and multi-display configurations. The 20 ray tracing cores enable hardware-accelerated ray tracing under DirectX 12 Ultimate. The PCIe 5.0 x16 interface provides high-bandwidth host communication. The four DisplayPort 2.1 outputs support modern high-refresh-rate and high-resolution monitors. The 550 W suggested PSU and single 8-pin connector define its power delivery requirements.

The 112EU Mobile is the only option in fanless, power-constrained mobile chassis. The B65 is the only option for users who need 32 GB of VRAM, ray tracing hardware, or PCIe 5.0 connectivity. The data shows no overlap in use cases: one is an integrated graphics solution, the other is a professional discrete workstation accelerator.