Intel Arc Graphics 128EU Mobile vs Intel Arc Graphics 4 Xe Mobile Comparison

Head-to-Head Benchmarks

The recorded data contains no direct head-to-head benchmark results for these two integrated graphics processors. Both entries list empty benchmark arrays, zero wins for either side, and no nearest rival comparisons. The database shows no aggregate score deltas, no percent differences, and no percentile shifts between the Intel Arc Graphics 128EU Mobile and the Intel Arc Graphics 4 Xe Mobile. Each unit holds a percentile rank of 50 against all GPUs in the database, though this rank is based on the overall distribution rather than a direct comparison between the two.

Without measured scores, the analysis must rely on the theoretical throughput figures recorded in the specification sheets. The 128EU part delivers 4.608 TFLOPS of FP32 compute, while the 4 Xe part delivers 2.355 TFLOPS. That places the 128EU at roughly 1.96 times the FP32 throughput of the 4 Xe, a near doubling of raw shader work per clock. The pixel rate follows the same pattern: 72.00 GPixel/s versus 36.80 GPixel/s, exactly a 2:1 ratio. Texture rate shows 144.0 GTexel/s against 73.60 GTexel/s, again a 2:1 ratio. These numbers are consistent with the shading unit counts, 1024 versus 512, and the TMU counts, 64 versus 32. The ROP count also doubles, 32 versus 16. Every fixed-function and shader-related rate in the pack scales precisely by a factor of two.

Boost clocks differ slightly. The 128EU boosts to 2250 MHz, while the 4 Xe boosts to 2300 MHz. That 50 MHz advantage for the smaller part does not offset the doubling of execution resources. The base clocks are identical at 300 MHz. Memory behavior is identical in kind: both use system shared memory, both have system dependent bandwidth, and both report a system shared bus width. No dedicated VRAM figures exist for either part.

Where Each One Wins

The 128EU Mobile wins on raw compute density and throughput in every measured rate category present in the pack. It doubles the FP32, FP16, pixel, and texture throughput of the 4 Xe part. For tasks that scale with shader count and texture units, such as general 3D rendering, higher resolution pixel fill, and compute workloads that are not bandwidth-limited, the 128EU holds a clear theoretical advantage. Its 1024 shading units and 64 TMUs give it more parallel work capacity per clock. The pixel rate of 72.00 GPixel/s suggests stronger fill performance for scenes with heavy overdraw or high resolution targets.

The 4 Xe Mobile wins on architectural recency and feature completeness. It uses the Xe3-LPG architecture on a 3 nm process node, while the 128EU uses the Xe-LPG architecture on a 10 nm node. The 4 Xe part supports DirectX 12 Ultimate (12_2), which is a higher feature level than the 12 (12_1) listed for the 128EU. It also includes 4 ray tracing cores, a feature entirely absent from the 128EU specification. The 4 Xe part lists power connectors as "None" while the 128EU lists no power connector field at all, and the 4 Xe shows a 25 W TDP versus 28 W for the 128EU. Lower power draw with a smaller process node makes the 4 Xe more suited to tight power envelopes in thin portable devices.

The 4 Xe also carries a higher boost clock, 2300 MHz versus 2250 MHz. In workloads that are latency-bound or that cannot use the full shader array of the 128EU, that clock advantage could translate into a small per-thread speedup. The 4 Xe has 4 RT cores, so any ray-traced workload that can use those cores will run on the 4 Xe but not on the 128EU, which lists no RT cores. The 128EU has no tensor core entry either, and neither part lists tensor cores, so AI acceleration differences cannot be established from the data.

Architecture Differences

The two processors come from different chip generations and architectures. The 128EU is built on the Meteor Lake chip with the Xe-LPG architecture, belonging to the Arc Graphics-M (Meteor Lake) generation. The 4 Xe is built on the Panther Lake chip with the Xe3-LPG architecture, belonging to the Arc Graphics-M (Panther Lake) generation. The process node moves from 10 nm for the 128EU to 3 nm for the 4 Xe, with the foundry listed as Intel for both. Transistor counts and die sizes are not recorded for the 128EU, while the 4 Xe lists both as "unknown". Transistor density is unrecorded for both.

The execution pipeline differs in scale. The 128EU has 1024 shading units, 64 texture mapping units, and 32 ROPs. The 4 Xe has 512 shading units, 32 TMUs, and 16 ROPs. The 4 Xe adds 4 ray tracing cores, which the 128EU does not list. Neither part lists tensor cores. The 128EU reports FP16 at 9.216 TFLOPS (2:1), while the 4 Xe reports FP16 at 4.710 TFLOPS (2:1). The 2:1 ratio notation indicates packed FP16 execution on both parts.

API support differs on the DirectX side. The 128EU lists DirectX 12 (12_1). The 4 Xe lists DirectX 12 Ultimate (12_2), a higher feature level that typically includes hardware ray tracing and mesh shaders. OpenGL is 4.6 for both, and Vulkan is 1.4 for both. The bus interface changes from "Ring Bus" on the 128EU to "IGP" on the 4 Xe. Both are IGP slot width, meaning integrated graphics with no add-in card form factor. Display outputs are portable device dependent for both.

Power delivery differs slightly. The 128EU has a TDP of 28 W. The 4 Xe has a TDP of 25 W. The 4 Xe lists power connectors as "None", while the 128EU leaves the field empty. Neither lists a suggested PSU. The release dates are far apart: the 128EU launched on 2023-12-13, while the 4 Xe launched on 2026-01-26. The 128EU lists its predecessor as HD Graphics-M, while the 4 Xe lists no predecessor. Both are marked as Active in production status.

FAQ

Q: Which GPU has more shading units?

A: The Intel Arc Graphics 128EU Mobile has 1024 shading units. The Intel Arc Graphics 4 Xe Mobile has 512 shading units, exactly half.

Q: Does the 4 Xe Mobile support hardware ray tracing?

A: Yes. The Intel Arc Graphics 4 Xe Mobile lists 4 ray tracing cores. The Intel Arc Graphics 128EU Mobile lists no ray tracing cores.

Q: What are the FP32 throughput figures for each?

A: The 128EU Mobile delivers 4.608 TFLOPS of FP32 compute. The 4 Xe Mobile delivers 2.355 TFLOPS. The 128EU has roughly 1.96 times the FP32 throughput.

Q: Which part has a higher boost clock?

A: The Intel Arc Graphics 4 Xe Mobile boosts to 2300 MHz. The Intel Arc Graphics 128EU Mobile boosts to 2250 MHz. The 4 Xe part is 50 MHz higher.

Q: Do the two GPUs support different DirectX feature levels?

A: Yes. The 128EU Mobile lists DirectX 12 (12_1). The 4 Xe Mobile lists DirectX 12 Ultimate (12_2), a higher feature level.

Q: What process nodes are used for each chip?

A: The 128EU Mobile uses a 10 nm process node. The 4 Xe Mobile uses a 3 nm process node. Both are fabricated by Intel.

The Verdict

The data supports a split decision based on workload type. For compute-heavy and fill-rate-heavy tasks that use the full shader array, the Intel Arc Graphics 128EU Mobile is the stronger part. It doubles the FP32, FP16, pixel, and texture throughput of the 4 Xe Mobile, and it has twice the shading units, TMUs, and ROPs. Its 28 W TDP is only 3 W higher than the 4 Xe part, so the throughput advantage does not come at a dramatically higher power cost. Any workload that is shader-bound, such as traditional rasterization, benefits from the 128EU.

For modern graphics features and ray tracing, the Intel Arc Graphics 4 Xe Mobile is the more capable part. It is the only one of the two with ray tracing cores, and it supports DirectX 12 Ultimate (12_2), which the 128EU does not. Its 3 nm process node and lower 25 W TDP make it a better fit for power-constrained designs. Its higher boost clock of 2300 MHz provides a small clock advantage over the 128EU, though that advantage does not compensate for the halved shader count in throughput-bound scenarios.

The release timeline matters for platform integration. The 128EU launched on 2023-12-13 with Meteor Lake. The 4 Xe launched on 2026-01-26 with Panther Lake. A system built around one chip will not accept the other, so the choice is tied to the platform generation. The 128EU is the compute leader in the recorded rates, while the 4 Xe is the feature leader with RT support and a newer architecture.

Specification Differences

| Field | Intel Arc Graphics 128EU Mobile | Intel Arc Graphics 4 Xe Mobile |

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

| Chip | Meteor Lake | Panther Lake |

| Architecture | Xe-LPG | Xe3-LPG |

| Generation | Arc Graphics-M (Meteor Lake) | Arc Graphics-M (Panther Lake) |

| Process node | 10 nm | 3 nm |

| Boost clock | 2250 MHz | 2300 MHz |

| Shading units | 1024 | 512 |

| TMUs | 64 | 32 |

| ROPs | 32 | 16 |

| Ray tracing cores | None listed | 4 |

| Pixel rate | 72.00 GPixel/s | 36.80 GPixel/s |

| Texture rate | 144.0 GTexel/s | 73.60 GTexel/s |

| FP32 | 4.608 TFLOPS | 2.355 TFLOPS |

| FP16 | 9.216 TFLOPS (2:1) | 4.710 TFLOPS (2:1) |

| TDP | 28 W | 25 W |

| Power connectors | Not listed | None |

| Bus interface | Ring Bus | IGP |

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

| Release date | 2023-12-13 | 2026-01-26 |

| Predecessor | HD Graphics-M | None listed |

| Transistors | Not listed | Unknown |

| Die size | Not listed | Unknown |

Both parts share the same base clock of 300 MHz, system shared memory with system dependent bandwidth, OpenGL 4.6, Vulkan 1.4, IGP slot width, portable device dependent display outputs, and Active production status. Neither lists a launch MSRP. The 128EU uses a Ring Bus interface while the 4 Xe uses an IGP bus interface, which reflects the different integration approaches of the two platform generations.