Intel Arc 140T Mobile vs Intel Arc Pro B65 Comparison

Where Each One Wins

The benchmark database records no direct head-to-head benchmark comparisons for these two GPUs, so the wins split must be inferred from their architectural and specification-level data. The Intel Arc 140T Mobile is an integrated graphics processor built into an Arrow Lake-H chip, operating as an IGP with system-shared memory. Its strength is efficiency and mobility: a 35 W TDP, a 300 MHz base clock with a 2350 MHz boost, and a pixel rate of 75.20 GPixel/s with a texture rate of 150.4 GTexel/s. This part is designed for portable devices where power draw and physical footprint are constrained, and its display outputs are entirely dependent on the host device.

The Intel Arc Pro B65 is a discrete, dual-slot workstation card based on the BMG-G21 chip. It carries 32 GB of GDDR6 memory on a 256-bit bus, delivering 608.0 GB/s of bandwidth. Its base and boost clocks are both fixed at 2400 MHz, and it reaches 192.0 GPixel/s and 384.0 GTexel/s. The B65 uses a PCIe 5.0 x16 interface, draws up to 200 W with a single 8-pin power connector, and requires a 550 W suggested power supply. It outputs to 4x DisplayPort 2.1 connectors. All of these metrics point to a card intended for sustained, high-throughput compute and professional rendering workloads, not portable integration.

Where the 140T wins is in power envelope and integration. The 35 W TDP is dramatically lower than the B65's 200 W, and the IGP form factor means no additional power connectors or expansion slot is needed. For thin-and-light laptops and compact mobile systems, the 140T is the only viable option among the two. The B65 wins outright on raw throughput, memory capacity, memory bandwidth, and interface bandwidth. The shading unit count tells the same story: 1024 shading units on the 140T versus 2560 on the B65, with 64 TMUs and 32 ROPs versus 160 TMUs and 80 ROPs. The B65 also has 20 ray tracing cores versus 8 on the 140T.

The Verdict

The data indicates two different product categories. The Intel Arc 140T Mobile is for users who need integrated graphics inside a mobile processor, with system-shared memory and a 35 W power budget. It is the only choice for a portable device where the GPU is soldered onto the CPU package. The Intel Arc Pro B65 is for professional workstations requiring 32 GB of dedicated GDDR6 memory, 608.0 GB/s of bandwidth, and a 200 W discrete card with PCIe 5.0 x16 connectivity. Anyone needing sustained compute, large datasets in memory, or multi-display professional output should select the B65 based on the recorded specifications.

The benchmark database does not provide comparative scores for these two parts, so a performance-per-watt calculation is not possible from the available data. However, the absolute numbers are unambiguous: the B65 delivers 12.29 TFLOPS FP32 versus 4.813 TFLOPS on the 140T, and 24.58 TFLOPS FP16 versus 9.626 TFLOPS FP16. The B65's memory bandwidth is 608.0 GB/s, while the 140T's bandwidth is listed as system dependent, meaning it has no fixed dedicated memory path. For any workload where memory capacity or bandwidth is the bottleneck, the B65 is the clear selection. For any system where power draw and physical integration are the primary constraints, the 140T is the only option.

Head-to-Head Benchmarks

The database contains no recorded head-to-head benchmark entries for the Intel Arc 140T Mobile versus the Intel Arc Pro B65, nor does it list nearest rivals for either product. The wins must therefore be assessed from the specification sheets.

The largest win for the Arc Pro B65 is in FP32 compute. The B65 records 12.29 TFLOPS, which is roughly 2.55 times the 140T's 4.813 TFLOPS. In FP16, the B65 delivers 24.58 TFLOPS, approximately 2.55 times the 140T's 9.626 TFLOPS as well. The pixel rate favors the B65 by a similar margin: 192.0 GPixel/s versus 75.20 GPixel/s, a factor of about 2.55. The texture rate shows 384.0 GTexel/s against 150.4 GTexel/s, again roughly 2.55 times higher on the B65.

Memory is the most dramatic separation. The B65 has 32 GB of GDDR6 on a 256-bit bus with 608.0 GB/s of bandwidth. The 140T uses system-shared memory with a system-shared bus width and system-dependent bandwidth. There is no fixed memory specification for the 140T, which means its memory performance cannot be directly quantified in the database. The B65's fixed 608.0 GB/s is a concrete advantage for any memory-intensive workload.

Clock speeds show a different relationship. The 140T has a base clock of 300 MHz and a boost of 2350 MHz, while the B65 runs at a flat 2400 MHz for both base and boost. The 140T's boost clock is close to the B65's fixed clock, but the 140T's base clock is drastically lower, indicating power-saving idle behavior typical of integrated graphics. The B65 maintains its full clock continuously, consistent with a discrete card that has dedicated cooling and a 200 W power budget.

Ray tracing hardware also favors the B65: 20 RT cores versus 8. Both parts support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API feature levels are identical. The B65's 2560 shading units, 160 TMUs, and 80 ROPs all outnumber the 140T's 1024, 64, and 32 respectively.

The 140T's only numerical wins are the lower TDP (35 W versus 200 W) and the integrated form factor. Its release date of January 12, 2025 predates the B65's March 31, 2026 release, making the 140T the earlier product. The B65 has a larger die at 272 mm² with 19,600 million transistors and a transistor density of 72.1M per mm², while the 140T's transistor count and die size are unknown in the database. Both use TSMC's 5 nm process node.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Intel Arc Pro B65 records 12.29 TFLOPS FP32, which is approximately 2.55 times the Intel Arc 140T Mobile's 4.813 TFLOPS.

Q: How much memory does each GPU have?

A: The Intel Arc Pro B65 has 32 GB of GDDR6 memory on a 256-bit bus. The Intel Arc 140T Mobile uses system-shared memory with no fixed size, type, or bus width listed in the database.

Q: What is the power consumption difference?

A: The Intel Arc 140T Mobile has a 35 W TDP. The Intel Arc Pro B65 has a 200 W TDP and requires a 550 W suggested power supply.

Q: Do both GPUs support the same graphics APIs?

A: Yes. Both the Intel Arc 140T Mobile and the Intel Arc Pro B65 support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What are the ray tracing core counts?

A: The Intel Arc Pro B65 has 20 ray tracing cores. The Intel Arc 140T Mobile has 8 ray tracing cores.

Q: Which GPU uses a discrete expansion slot?

A: The Intel Arc Pro B65 is a dual-slot card using a PCIe 5.0 x16 interface with a single 8-pin power connector. The Intel Arc 140T Mobile is an integrated GPU (IGP) with no expansion slot or power connectors.

Architecture Differences

The Intel Arc 140T Mobile is built on the Xe-LPG+ architecture as part of the Arc Graphics-M (Arrow Lake) generation, using an Arrow Lake-H chip. The Intel Arc Pro B65 uses the Xe2-HPG architecture from the Battlemage (Pro Series) generation, built on the BMG-G21 chip. Both are fabricated on TSMC's 5 nm process, but the architectural generations are distinct: Xe-LPG+ is the mobile integrated variant, while Xe2-HPG is the discrete workstation design.

The process node is identical at 5 nm, but the physical implementation differs sharply. The B65 has a die size of 272 mm² with 19,600 million transistors, yielding a transistor density of 72.1M per mm². The 140T's die size and transistor count are listed as unknown in the database. The B65 is a large discrete chip, while the 140T is integrated into the Arrow Lake-H processor package.

Memory architecture is fundamentally different. The 140T uses system-shared memory, meaning it borrows from the host system's RAM with no dedicated VRAM, bus width, or bandwidth figure. The B65 has 32 GB of dedicated GDDR6 memory on a 256-bit bus with 608.0 GB/s of bandwidth and a 2375 MHz memory clock running at 19 Gbps effective. This makes the B65 suitable for workloads that require large resident datasets, while the 140T's memory performance is entirely dependent on the host system's memory configuration.

The compute resources scale accordingly. The 140T has 1024 shading units, 64 TMUs, 32 ROPs, and 8 RT cores. The B65 has 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores. The B65's pixel rate is 192.0 GPixel/s versus 75.20 GPixel/s on the 140T, and its texture rate is 384.0 GTexel/s versus 150.4 GTexel/s. FP32 and FP16 rates follow the same proportional relationship.

Clock behavior differs by design. The 140T operates at a 300 MHz base clock and boosts to 2350 MHz, reflecting a power-conscious mobile design that ramps up under load. The B65 runs at a constant 2400 MHz for both base and boost, indicating a workstation card that maintains sustained clocks under continuous load. The power delivery reflects this: the 140T is rated at 35 W with no power connectors, while the B65 draws 200 W through a single 8-pin connector and requires a 550 W suggested power supply.

The bus interface separates the two categories. The 140T uses an IGP interface with no expansion slot, and its display outputs are portable-device dependent. The B65 uses PCIe 5.0 x16 and provides 4x DisplayPort 2.1 outputs, enabling multi-monitor professional setups. Both parts are currently active in production, with the 140T released on January 12, 2025 and the B65 on March 31, 2026. The 140T lists HD Graphics-M as its predecessor, while the B65 has no predecessor recorded. Neither part has a successor listed in the database.