Intel Arc Graphics 128EU Mobile vs Intel Arc Pro B65 Comparison

Intel Arc Graphics 128EU Mobile and Intel Arc Pro B65 occupy different ends of Intel’s graphics portfolio. The former is a 28 W integrated solution for Meteor Lake laptops, while the latter is a 200 W dual-slot discrete workstation card built on the Battlemage architecture. The database records show both GPUs at the 50th percentile among all measured graphics processors, but their specifications and intended roles diverge sharply.

Head-to-Head Benchmarks

The database contains no direct benchmark scores for either GPU, so the comparison relies on theoretical peak rates and raw specification deltas. The Arc Pro B65 delivers 12.29 TFLOPS of FP32 compute, which is 2.67 times the 4.608 TFLOPS of the Arc Graphics 128EU Mobile. That ratio holds across texture and pixel throughput: the Pro B65 reaches 384.0 GTexel/s versus 144.0 GTexel/s for the mobile part, a 2.67x advantage, and 192.0 GPixel/s versus 72.00 GPixel/s, also a 2.67x gap. These consistent multiples indicate the two designs scale linearly with their shading unit counts.

The mobile GPU uses 1024 shading units, 64 texture mapping units, and 32 raster operation pipelines. The Pro B65 doubles those counts to 2560 shading units, 160 TMUs, and 80 ROPs. The arithmetic is straightforward: the Pro B65 has 2.5 times the shader cores, 2.5 times the texture units, and 2.5 times the ROPs. The FP32, texture, and pixel rate figures all align with these ratios, confirming that clock speed differences do not distort the relative performance picture.

Clock behavior favors the discrete card in a different way. The Arc Pro B65 runs at a flat 2400 MHz for both base and boost, whereas the Arc Graphics 128EU Mobile spans 300 MHz base to 2250 MHz boost. The integrated part’s boost clock reaches 93.75% of the discrete card’s fixed clock, yet its much smaller execution resource pool limits aggregate throughput. The mobile GPU’s low 300 MHz base clock reflects power management for thin-and-light systems, while the Pro B65’s unwavering 2400 MHz indicates a desktop-oriented design that sustains peak frequency under load.

Memory bandwidth creates the largest practical divide. The Arc Pro B65 pairs 32 GB of GDDR6 on a 256 bit bus with 608.0 GB/s of bandwidth. The Arc Graphics 128EU Mobile uses system shared memory, and its bandwidth is listed as system dependent. In a laptop with dual-channel DDR5, shared memory bandwidth would typically fall far below 608.0 GB/s, making the discrete card’s advantage in bandwidth-bound workloads even more pronounced than the compute ratios suggest.

Ray tracing further separates the two. The Pro B65 includes 20 dedicated ray tracing cores, while the mobile GPU lists no ray tracing cores at all. Any workload that uses hardware-accelerated ray tracing will run exclusively on the discrete part. The mobile GPU can still render scenes with software-based ray tracing, but the database records no dedicated hardware for it.

FAQ

Q: How much faster is the Intel Arc Pro B65 than the Intel Arc Graphics 128EU Mobile in raw compute?

A: The Arc Pro B65 delivers 12.29 TFLOPS FP32, which is 2.67 times the 4.608 TFLOPS of the mobile GPU. The same 2.67x ratio applies to pixel rate (192.0 GPixel/s versus 72.00 GPixel/s) and texture rate (384.0 GTexel/s versus 144.0 GTexel/s).

Q: Why does the mobile GPU show a 300 MHz base clock?

A: The Arc Graphics 128EU Mobile is an integrated processor graphics solution rated at 28 W TDP. Its 300 MHz base clock is a power-saving floor for idle and light loads, while the 2250 MHz boost clock handles demanding tasks. The Arc Pro B65, by contrast, runs at a constant 2400 MHz with no clock variation between base and boost.

Q: Does the Arc Graphics 128EU Mobile support hardware ray tracing?

A: The database lists no ray tracing cores for the Arc Graphics 128EU Mobile. The Arc Pro B65 includes 20 ray tracing cores. This means hardware-accelerated ray tracing is only available on the discrete Battlemage card.

Q: What memory configuration does each GPU use?

A: The Arc Graphics 128EU Mobile uses system shared memory with system dependent bandwidth. The Arc Pro B65 has 32 GB of GDDR6 on a 256 bit bus, delivering 608.0 GB/s at 2375 MHz (19 Gbps effective).

Q: How do the two GPUs compare in API support?

A: Both support OpenGL 4.6 and Vulkan 1.4. The DirectX support differs: the Arc Pro B65 supports DirectX 12 Ultimate (12_2), while the mobile GPU supports DirectX 12 (12_1). The Ultimate designation reflects the discrete card’s ray tracing and mesh shader capabilities.

Q: Which GPU has a higher pixel fill rate?

A: The Arc Pro B65 achieves 192.0 GPixel/s, exactly 2.67 times the 72.00 GPixel/s of the Arc Graphics 128EU Mobile. This difference comes from the Pro B65’s 80 ROPs versus the mobile GPU’s 32 ROPs, combined with the clock speed advantage.

Architecture Differences

The two GPUs come from different architectural generations. The Arc Graphics 128EU Mobile uses the Xe-LPG architecture on Intel’s Meteor Lake chip, built on a 10 nm process at Intel’s own foundry. The Arc Pro B65 uses the Xe2-HPG architecture on the BMG-G21 chip, part of the Battlemage (Pro Series) generation, fabricated by TSMC on a 5 nm process. The process node difference is significant: 5 nm allows nearly double the transistor density of 10 nm, which helps explain how the Pro B65 fits 19,600 million transistors into a 272 mm² die, yielding a density of 72.1M transistors per mm². The mobile GPU’s transistor count and die size are not recorded in the database, but its integrated nature means it shares silicon with the CPU rather than existing as a separate die.

The memory architecture reflects the fundamental use case difference. The mobile GPU uses system shared memory with no dedicated VRAM, a design choice for power efficiency and cost reduction in laptops. The Pro B65 carries 32 GB of dedicated GDDR6 memory with a 256 bit bus and 608.0 GB/s bandwidth. The memory clock runs at 2375 MHz with 19 Gbps effective data rate, which is a fixed specification rather than the system dependent figure listed for the mobile part.

The execution pipelines differ in scale and capability. The Pro B65 has 2560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores. The mobile GPU has 1024 shading units, 64 TMUs, and 32 ROPs, with no ray tracing cores listed. The Pro B65’s larger pipeline supports higher FP16 throughput at 24.58 TFLOPS (2:1 ratio) versus 9.216 TFLOPS (2:1) for the mobile GPU.

The power delivery and physical design differ completely. The mobile GPU is an IGP with a 28 W TDP and no power connectors, designed to be soldered onto a laptop motherboard. The Pro B65 is a dual-slot discrete card with a 200 W TDP, one 8-pin power connector, and a suggested 550 W power supply. The bus interface also differs: the mobile GPU uses a Ring Bus (internal to the Meteor Lake chip), while the Pro B65 uses PCIe 5.0 x16 for external connectivity.

Display output capabilities reflect the target platforms. The Pro B65 offers four DisplayPort 2.1 outputs, suitable for multi-monitor professional workstations. The mobile GPU’s display outputs are listed as portable device dependent, meaning they vary by laptop design and typically include embedded panel connections plus a limited set of external ports.

The release timeline shows the mobile GPU arriving first: it launched on December 13, 2023, with the Arc Pro B65 following on March 31, 2026. The mobile GPU’s predecessor is recorded as HD Graphics-M, while the Pro B65 has no predecessor listed in the database. Both remain in active production.

The Verdict

The data points to two distinct purchasing decisions based on workload requirements and platform constraints. The Arc Graphics 128EU Mobile is the only option for thin-and-light laptops that need basic 3D acceleration without a discrete GPU. Its 28 W TDP, system shared memory, and Ring Bus interface tie it to the Meteor Lake platform. The 50th percentile ranking places it in the middle of all measured GPUs, which is respectable for an integrated solution but insufficient for demanding professional tasks.

The Arc Pro B65 is the clear choice for workstation-class workloads that require sustained compute throughput, large memory capacity, and hardware ray tracing. Its 12.29 TFLOPS FP32 performance, 32 GB GDDR6 memory, and 608.0 GB/s bandwidth address professional rendering, simulation, and AI inference tasks that would overwhelm the mobile GPU’s shared memory subsystem. The 20 ray tracing cores and DirectX 12 Ultimate support enable hardware-accelerated ray tracing, a feature entirely absent from the mobile part.

The 200 W TDP and dual-slot form factor make the Pro B65 unsuitable for portable systems, while the mobile GPU’s 28 W TDP and IGP design preclude desktop workstation use. The choice is not about which GPU is better in absolute terms, but which platform constraint applies. Users with a Meteor Lake laptop get the Arc Graphics 128EU Mobile as an integrated component. Users building a professional workstation with PCIe 5.0 and a 550 W power supply select the Arc Pro B65.

The performance ratio of 2.67x across compute, texture, and pixel rates provides a reliable expectation for relative speed in shader-bound workloads. The memory bandwidth gap, while not quantified as a ratio due to the mobile GPU’s system dependent figure, is substantial: 608.0 GB/s dedicated bandwidth versus whatever the host laptop’s memory subsystem provides. For bandwidth-intensive tasks like large texture streaming or data-parallel compute, the discrete card’s advantage will exceed the 2.67x compute ratio.

Both GPUs sit at the 50th percentile in the database, indicating they represent median performance among all recorded graphics processors. The Arc Pro B65 achieves this with a 200 W power envelope, while the Arc Graphics 128EU Mobile does so within a 28 W envelope. The power efficiency comparison favors the mobile part, but the absolute performance comparison favors the discrete card. Neither GPU shows a clear specification advantage in every category, but the Arc Pro B65 dominates in raw throughput, memory capacity, and feature support.

Specification Differences

The recorded specifications show the following differences between the two GPUs:

• Chip and architecture: Intel Arc Graphics 128EU Mobile uses the Meteor Lake chip with Xe-LPG architecture. The Arc Pro B65 uses the BMG-G21 chip with Xe2-HPG architecture.
• Process node and foundry: The mobile GPU uses 10 nm at Intel. The Pro B65 uses 5 nm at TSMC.
• Transistors and die size: The Pro B65 has 19,600 million transistors on a 272 mm² die with 72.1M / mm² density. The mobile GPU’s figures are not recorded.
• Base clock: 300 MHz for the mobile GPU versus 2400 MHz for the Pro B65.
• Boost clock: 2250 MHz for the mobile GPU versus 2400 MHz for the Pro B65 (no boost variation).
• Memory clock: System shared for the mobile GPU versus 2375 MHz (19 Gbps effective) for the Pro B65.
• Memory size: System shared versus 32 GB GDDR6.
• Memory bus width: System shared versus 256 bit.
• Memory bandwidth: System dependent versus 608.0 GB/s.
• Shading units: 1024 versus 2560.
• Texture mapping units: 64 versus 160.
• Raster operation pipelines: 32 versus 80.
• Ray tracing cores: None listed versus 20.
• Pixel rate: 72.00 GPixel/s versus 192.0 GPixel/s.
• Texture rate: 144.0 GTexel/s versus 384.0 GTexel/s.
• FP32 performance: 4.608 TFLOPS versus 12.29 TFLOPS.
• FP16 performance: 9.216 TFLOPS (2:1) versus 24.58 TFLOPS (2:1).
• TDP: 28 W versus 200 W.
• Slot width: IGP versus dual-slot.
• Power connectors: None versus 1x 8-pin.
• Suggested PSU: Not listed versus 550 W.
• Bus interface: Ring Bus versus PCIe 5.0 x16.
• Display outputs: Portable device dependent versus 4x DisplayPort 2.1.
• DirectX support: 12 (12_1) versus 12 Ultimate (12_2).
• Release date: December 13, 2023 versus March 31, 2026.
• Predecessor: HD Graphics-M versus none recorded.

The two GPUs share several traits: both are made by Intel, both support OpenGL 4.6 and Vulkan 1.4, both are in active production, neither has a recorded launch MSRP, and both rank at the 50th percentile among all GPUs in the database. No benchmark scores or nearest rival data are recorded for either part, so the specification comparison above represents the complete quantitative picture available.