Intel Arc 140T Mobile vs Intel Arc A380E Comparison

Head-to-Head Benchmarks

The recorded data contains no direct benchmark scores for either the Intel Arc 140T Mobile or the Intel Arc A380E. Both entries show an average benchmark score of 0 and no head-to-head results. The absence of measured performance data means no comparative frame rates, synthetic scores, or compute workloads can be cited from the database. The percentileVsAllGpus field places both parts at the 50th percentile, indicating they sit at the midpoint of all recorded GPUs, but this is a relative rank rather than a raw performance figure.

Without benchmark results, the analysis shifts to the derived specifications that determine performance. The Arc 140T Mobile delivers a peak FP32 throughput of 4.813 TFLOPS, while the Arc A380E reaches 4.096 TFLOPS. That difference, roughly 17.5% in favor of the mobile part, comes from the Arc 140T's 2350 MHz boost clock versus the Arc A380E's fixed 2000 MHz clock. The pixel rate tells a similar story: 75.20 GPixel/s for the Arc 140T Mobile against 64.00 GPixel/s for the Arc A380E. The texture rate follows, with 150.4 GTexel/s on the mobile chip and 128.0 GTexel/s on the embedded card. These derived rates all stem from the same 1024 shading units, 64 texture mapping units, 32 ROPs, and 8 ray tracing cores found on both parts.

The FP16 figures mirror the FP32 relationship. The Arc 140T Mobile lists 9.626 TFLOPS at a 2:1 ratio, and the Arc A380E lists 8.192 TFLOPS under the same 2:1 ratio. The mobile part holds a consistent advantage across every compute metric recorded in the database. However, the A380E counters with a dedicated memory subsystem. It uses 6 GB of GDDR6 on a 96-bit bus, delivering 186.0 GB/s of bandwidth. The Arc 140T Mobile relies on system shared memory, with bandwidth listed as system dependent. That architectural split means the embedded card has deterministic memory performance, while the mobile chip's effective bandwidth varies with the host platform's memory configuration.

Architecture Differences

The two GPUs come from different Intel architectures and process nodes. The Arc 140T Mobile uses the Xe-LPG+ architecture on a 5 nm process from TSMC, built on the Arrow Lake-H chip. The Arc A380E uses the Xe-HPG architecture on a 6 nm process from TSMC, built on the DG2-128 chip. The process node difference gives the mobile part a density advantage, although the database does not list transistor counts or die size for the Arc 140T. The A380E is fully documented: 7,200 million transistors on a 157 mm² die, yielding a transistor density of 45.9M per mm².

The compute block layout is identical. Both parts feature 1024 shading units, 64 TMUs, 32 ROPs, and 8 RT cores. Neither lists tensor cores. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The core difference beyond the node is the clock behavior. The Arc 140T Mobile has a 300 MHz base clock and a 2350 MHz boost clock, allowing dynamic frequency scaling. The Arc A380E runs at a flat 2000 MHz for both base and boost, which is typical for an embedded or industrial card where consistent performance matters more than burst capability.

The production status differs sharply. The Arc 140T Mobile is listed as Active and was released on 2025-01-12. The Arc A380E is listed as End-of-life and was released on 2024-03-31, with Battlemage listed as its successor. The Arc 140T Mobile's predecessor is HD Graphics-M, while the A380E's predecessor is Xe Graphics. The mobile part belongs to the Arc Graphics-M (Arrow Lake) generation, and the A380E belongs to the Alchemist (Arc 3) generation.

FAQ

Q: Which GPU has higher raw compute throughput?

A: The Intel Arc 140T Mobile leads in every compute metric. It delivers 4.813 TFLOPS FP32 versus 4.096 TFLOPS for the Arc A380E, and 9.626 TFLOPS FP16 versus 8.192 TFLOPS for the A380E.

Q: Why does the Arc 140T Mobile achieve higher performance despite the same core counts?

A: Both GPUs have 1024 shading units, 64 TMUs, 32 ROPs, and 8 RT cores. The difference comes from the clock speed: the Arc 140T Mobile boosts to 2350 MHz, while the Arc A380E is locked at 2000 MHz.

Q: Does the Arc A380E have any advantage over the mobile part?

A: Yes, in memory. The Arc A380E has 6 GB of dedicated GDDR6 on a 96-bit bus with 186.0 GB/s bandwidth. The Arc 140T Mobile uses system shared memory, and its bandwidth is system dependent.

Q: Are the two GPUs from the same architecture generation?

A: No. The Arc 140T Mobile uses Xe-LPG+ on a 5 nm node, and the Arc A380E uses Xe-HPG on a 6 nm node. They also use different chips: Arrow Lake-H versus DG2-128.

Q: What is the power draw difference?

A: The Arc 140T Mobile is rated at 35 W TDP, and the Arc A380E is rated at 75 W TDP. The A380E also lists a suggested PSU of 250 W, while the mobile part is an integrated GPU with no power connector requirement.

Q: Which GPU is still in production?

A: The Arc 140T Mobile is listed as Active with a 2025-01-12 release date. The Arc A380E is listed as End-of-life with a 2024-03-31 release date.

The Verdict

The data points to a clear split between the two products. The Arc 140T Mobile is the faster part on paper, with a 17.5% lead in FP32 throughput, a 17.5% lead in pixel rate, and a 17.5% lead in texture rate. It also consumes less power, at 35 W versus 75 W, and is built on a smaller 5 nm node versus the A380E's 6 nm node. It is the active product, released later, and designed for the Arrow Lake-H mobile platform.

The Arc A380E has one structural advantage: dedicated memory. The 6 GB GDDR6 pool with 186.0 GB/s bandwidth is a fixed resource, independent of the host system. The Arc 140T Mobile's system shared memory means its real-world bandwidth depends entirely on the laptop or mini PC it sits in. For workloads that stress memory bandwidth, the A380E's deterministic 186.0 GB/s could offset some of the mobile part's compute lead, but the database does not provide benchmark scores to confirm that.

The production status is decisive for new designs. The Arc 140T Mobile is Active; the Arc A380E is End-of-life. The A380E's successor, Battlemage, is already listed. Anyone selecting a new part from this data would choose the Arc 140T Mobile for compute performance, power efficiency, and longevity. The A380E remains relevant only for systems that require a discrete card with dedicated memory and a fixed clock, such as embedded deployments where predictability outweighs peak throughput.

Specification Differences

| Field | Intel Arc 140T Mobile | Intel Arc A380E |

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

| Architecture | Xe-LPG+ | Xe-HPG |

| Process node | 5 nm | 6 nm |

| Transistors | unknown | 7,200 million |

| Die size | unknown | 157 mm² |

| Base clock | 300 MHz | 2000 MHz |

| Boost clock | 2350 MHz | 2000 MHz |

| Memory size | System Shared | 6 GB |

| Memory type | System Shared | GDDR6 |

| Memory bus | System Shared | 96 bit |

| Memory bandwidth | System Dependent | 186.0 GB/s |

| Pixel rate | 75.20 GPixel/s | 64.00 GPixel/s |

| Texture rate | 150.4 GTexel/s | 128.0 GTexel/s |

| FP32 | 4.813 TFLOPS | 4.096 TFLOPS |

| FP16 | 9.626 TFLOPS (2:1) | 8.192 TFLOPS (2:1) |

| TDP | 35 W | 75 W |

| Slot width | IGP | Single-slot |

| Power connectors | None | None |

| Suggested PSU | None | 250 W |

| Bus interface | IGP | PCIe 4.0 x8 |

| Display outputs | Portable Device Dependent | 4x DisplayPort 2.0 |

| Dimensions | Not listed | 254 mm x 127 mm x 20 mm |

| Production status | Active | End-of-life |

| Release date | 2025-01-12 | 2024-03-31 |

| Predecessor | HD Graphics-M | Xe Graphics |

| Successor | None | Battlemage |

Where Each One Wins

The Arc 140T Mobile wins on every computed throughput metric recorded in the database. It leads in FP32, FP16, pixel rate, and texture rate. It also wins on power efficiency, drawing 35 W versus the A380E's 75 W. Its 5 nm process node and 2350 MHz boost clock deliver that advantage while remaining an integrated GPU with no separate power connector. It is the correct choice for a mobile platform built on Arrow Lake-H, where the system memory is shared and the power budget is tight.

The Arc A380E wins on memory determinism and physical integration. Its 6 GB GDDR6 with 186.0 GB/s bandwidth is a known quantity, unaffected by host memory speed or allocation. It runs at a fixed 2000 MHz clock, which removes boost variability and suits applications that need repeatable performance. It is a single-slot card with four DisplayPort 2.0 outputs, a PCIe 4.0 x8 interface, and a 250 W suggested PSU. Those features make it a fit for embedded systems, signage, or industrial machines where a standalone card with fixed memory is required. The data also shows it is end-of-life, so new deployments should account for its successor, Battlemage.