AMD Instinct MI350P vs Intel Arc 140T Mobile Comparison

The AMD Instinct MI350P and Intel Arc 140T Mobile occupy opposite ends of the hardware spectrum, yet both are recorded in the database with a 50th percentile ranking among all GPUs. The data reveals two devices engineered for fundamentally different tasks, with no overlapping benchmark wins. The MI350P is a dual-slot, 600 W accelerator with no display outputs, while the Arc 140T is a 35 W integrated processor for portable devices. Their shared percentile standing is a statistical coincidence, not a sign of comparable capability.

Where Each One Wins

The AMD Instinct MI350P holds every recorded performance advantage due to its sheer scale. It uses 8192 shading units, 512 texture mapping units, and a 8192-bit memory bus, making it a compute-oriented accelerator. The Intel Arc 140T Mobile counters with 1024 shading units, 64 TMUs, and 32 ROPs, figures that place it firmly in the integrated graphics category. The MI350P wins in raw throughput, memory bandwidth, and texture processing, while the Arc 140T wins in power efficiency, portability, and feature support for consumer graphics APIs.

The Arc 140T is the only one of the two with display outputs, listed as "Portable Device Dependent," and it supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The MI350P has no display outputs and its API support is marked as N/A, indicating it is not designed for rendering to a screen. The use-case split is clear: the MI350P targets server-side compute workloads, while the Arc 140T serves mobile graphics and media tasks.

Architecture Differences

The MI350P uses the CDNA 4.0 architecture on a 3 nm TSMC process, with 73,000 million transistors on a 1190 mm² die. Its transistor density is recorded at 61.3M per mm². The Arc 140T uses the Xe-LPG+ architecture on a 5 nm TSMC process, with transistor count and die size listed as unknown. The MI350P is built for pure compute, evidenced by its 0 ROPs and 0 MPixel/s pixel rate, while the Arc 140T has 32 ROPs and a 75.20 GPixel/s pixel rate.

Memory architecture differs fundamentally. The MI350P features 144 GB of HBM3e memory with a 8192-bit bus and 8.19 TB/s bandwidth, with memory clocked at 2000 MHz (8 Gbps effective). The Arc 140T uses System Shared memory, with bus width and bandwidth both marked as System Dependent. Clock speeds also diverge: the MI350P runs at 1000 MHz base and 2200 MHz boost, while the Arc 140T runs at 300 MHz base and 2350 MHz boost. The MI350P has a higher base clock but a lower boost clock, reflecting its steady-state compute design.

The MI350P includes ray tracing cores marked as null, while the Arc 140T has 8 ray tracing cores. The MI350P also has no listed tensor cores. Power delivery differs sharply: the MI350P requires a 1000 W suggested PSU and a single 16-pin connector, while the Arc 140T has no power connectors and is integrated into the processor. The MI350P is 267 mm long, 111 mm high, and 40 mm wide, while the Arc 140T has no recorded dimensions.

Head-to-Head Benchmarks

The database records zero head-to-head benchmarks between these two devices, and zero wins for either side. This absence of direct comparison data is itself informative. The MI350P and Arc 140T are so different in purpose that no common benchmark suite has been applied to both. The MI350P delivers 36.04 TFLOPS of FP32 and FP16 performance, while the Arc 140T delivers 4.813 TFLOPS FP32 and 9.626 TFLOPS FP16. That means the MI350P is roughly 7.5 times faster in FP32, a figure derived from the recorded numbers.

Texture rate shows a similar gap: the MI350P achieves 1,126.4 GTexel/s, while the Arc 140T achieves 150.4 GTexel/s. The MI350P is about 7.5 times faster in texture processing as well. However, the Arc 140T has a pixel rate of 75.20 GPixel/s, while the MI350P is recorded at 0 MPixel/s, so the Arc 140T is the only one capable of pixel output. The MI350P makes up for this with 8.19 TB/s of memory bandwidth, versus System Dependent bandwidth for the Arc 140T, a difference that heavily favors the MI350P for large data sets.

Boost clocks are close: 2200 MHz for the MI350P versus 2350 MHz for the Arc 140T. The MI350P compensates with far more execution units, but the Arc 140T's higher boost clock suggests better clock-for-clock efficiency in its design. The MI350P has a 600 W TDP, while the Arc 140T has a 35 W TDP, a 17-fold difference in power draw that explains the MI350P's need for a 1000 W suggested PSU.

The Verdict

The data indicates the AMD Instinct MI350P is for compute-heavy workloads that require massive memory capacity and bandwidth. Its 144 GB HBM3e memory, 8192-bit bus, and 8.19 TB/s bandwidth make it suitable for large-scale data processing, while its 36.04 TFLOPS FP32 performance positions it as a high-throughput accelerator. The lack of display outputs and API support confirms it is not meant for end-user graphics.

The Intel Arc 140T Mobile is for portable devices that need integrated graphics. Its 1024 shading units, 8 ray tracing cores, and support for DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4 make it a capable mobile GPU for consumer applications. Its 35 W TDP and System Shared memory align with laptop and handheld designs, and its 75.20 GPixel/s pixel rate allows for display output.

A user choosing between these two would select the MI350P for server or workstation compute tasks, and the Arc 140T for mobile graphics. The MI350P has no launch MSRP recorded, and neither does the Arc 140T. The MI350P releases on 2026-05-06, while the Arc 140T releases on 2025-01-12, making the Intel part earlier to market. The MI350P succeeds the Radeon Instinct line, while the Arc 140T succeeds HD Graphics-M, reflecting their different lineages.

FAQ

Q: Which GPU has more shading units?

A: The AMD Instinct MI350P has 8192 shading units, while the Intel Arc 140T Mobile has 1024 shading units, an 8-fold difference.

Q: Does the AMD Instinct MI350P support DirectX 12 Ultimate?

A: No, the database records its DirectX API support as N/A. The Intel Arc 140T Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the memory configuration of each GPU?

A: The MI350P has 144 GB of HBM3e memory on a 8192-bit bus with 8.19 TB/s bandwidth. The Arc 140T uses System Shared memory with System Dependent bus width and bandwidth.

Q: Which GPU has a higher boost clock?

A: The Intel Arc 140T Mobile has a boost clock of 2350 MHz, which is higher than the AMD Instinct MI350P's 2200 MHz boost clock.

Q: Can the AMD Instinct MI350P output to a display?

A: No, the database lists its display outputs as "No outputs." The Intel Arc 140T Mobile has display outputs marked as "Portable Device Dependent."

Q: What is the power consumption difference?

A: The MI350P has a TDP of 600 W and a suggested PSU of 1000 W, while the Arc 140T has a TDP of 35 W and no suggested PSU.

Specification Differences

The two GPUs differ in nearly every recorded specification. The MI350P uses a 3 nm process, while the Arc 140T uses a 5 nm process, both from TSMC. Transistor count is 73,000 million for the MI350P versus unknown for the Arc 140T. Die size is 1190 mm² for the MI350P versus unknown for the Arc 140T.

Clock speeds differ: base clock is 1000 MHz for the MI350P and 300 MHz for the Arc 140T. Boost clock is 2200 MHz for the MI350P and 2350 MHz for the Arc 140T. Memory clock is 2000 MHz (8 Gbps effective) for the MI350P, while the Arc 140T uses System Shared memory.

Memory size is 144 GB HBM3e for the MI350P versus System Shared for the Arc 140T. Bus width is 8192 bit for the MI350P versus System Shared for the Arc 140T. Bandwidth is 8.19 TB/s for the MI350P versus System Dependent for the Arc 140T.

Shading units count 8192 for the MI350P and 1024 for the Arc 140T. TMUs number 512 for the MI350P and 64 for the Arc 140T. ROPs are 0 for the MI350P and 32 for the Arc 140T. Ray tracing cores are null for the MI350P and 8 for the Arc 140T.

Pixel rate is 0 MPixel/s for the MI350P and 75.20 GPixel/s for the Arc 140T. Texture rate is 1,126.4 GTexel/s for the MI350P and 150.4 GTexel/s for the Arc 140T. FP32 performance is 36.04 TFLOPS for the MI350P and 4.813 TFLOPS for the Arc 140T. FP16 performance is 36.04 TFLOPS (1:1) for the MI350P and 9.626 TFLOPS (2:1) for the Arc 140T.

TDP is 600 W for the MI350P and 35 W for the Arc 140T. Slot width is Dual-slot for the MI350P and IGP for the Arc 140T. The MI350P uses a 1x 16-pin power connector, while the Arc 140T has none. The suggested PSU is 1000 W for the MI350P and null for the Arc 140T. Bus interface is PCIe 5.0 x16 for the MI350P and IGP for the Arc 140T. Display outputs are "No outputs" for the MI350P and "Portable Device Dependent" for the Arc 140T.

API support is N/A for the MI350P, while the Arc 140T supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Dimensions are 267 mm length, 111 mm height, and 40 mm width for the MI350P, with none recorded for the Arc 140T. Production status is null for the MI350P and Active for the Arc 140T. Release dates are 2026-05-06 for the MI350P and 2025-01-12 for the Arc 140T. Predecessors are Radeon Instinct for the MI350P and HD Graphics-M for the Arc 140T.