AMD Instinct MI350X vs Intel Arc 130V Mobile Comparison

FAQ

Q: What are the two products compared in this database entry?

A: The AMD Instinct MI350X, an OAM module accelerator built on the CDNA 4.0 architecture, and the Intel Arc 130V Mobile, an integrated GPU (IGP) based on the Xe2-LPG architecture within the Lunar Lake chip.

Q: When was each product released?

A: The Intel Arc 130V Mobile was released on 2024-09-23, while the AMD Instinct MI350X followed on 2025-06-11.

Q: What are the respective power requirements?

A: The AMD Instinct MI350X has a TDP of 1000 W and a suggested PSU rating of 1400 W, with no power connectors listed. The Intel Arc 130V Mobile has a TDP of 37 W.

Q: What is the difference in manufacturing process?

A: Both products are fabricated on a 3 nm process at TSMC, but the AMD chip has a die size of 2380 mm² with 185,000 million transistors, whereas the Intel chip has a die size of 172 mm² and an unknown transistor count.

Q: Does the AMD part support any display outputs?

A: No, the AMD Instinct MI350X has no display outputs, as it is designed as an OAM module for compute workloads. The Intel Arc 130V Mobile's display outputs are listed as Portable Device Dependent.

Q: What is the memory configuration for each?

A: The AMD Instinct MI350X uses 288 GB of HBM3e memory on a 8192-bit bus with 8.19 TB/s bandwidth. The Intel Arc 130V Mobile uses system shared memory, with system dependent bandwidth.

Architecture Differences

The AMD Instinct MI350X and Intel Arc 130V Mobile represent two fundamentally different design philosophies within the same 3 nm TSMC manufacturing node. The MI350X is a discrete, OAM form factor accelerator built on AMD's CDNA 4.0 architecture, explicitly engineered for data center compute. Its physical scale is substantial: a die size of 2380 mm² containing 185,000 million transistors, yielding a transistor density of 77.7M per mm². The chip is identified as MI350 256CU, and its shading unit count reaches 16,384, with 1024 texture mapping units and no raster output pipelines, reflecting its compute-first orientation.

The Intel Arc 130V Mobile, by contrast, is an integrated GPU within the Lunar Lake processor, built on the Xe2-LPG architecture. It occupies a die size of 172 mm², though the database lists its transistor count as unknown. This IGP is far smaller in execution resources: 896 shading units, 56 TMUs, 28 ROPs, and 7 ray tracing cores. The architectural split is clear: the MI350X omits ray tracing hardware entirely and reports zero pixel rate, while the Arc 130V includes dedicated RT cores and a pixel rate of 51.80 GPixel/s. The MI350X also reports no API support for DirectX, OpenGL, or Vulkan, whereas the Arc 130V supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Clock behavior diverges sharply. The MI350X runs at a base clock of 1000 MHz with a boost of 2200 MHz, while the Arc 130V operates at a base of 300 MHz and boosts to 1850 MHz. Memory architecture is another major divider: the MI350X uses 288 GB of HBM3e on a 8192-bit bus, delivering 8.19 TB/s of bandwidth, while the Arc 130V relies on system shared memory with system dependent bandwidth. The MI350X's memory clock is listed at 2000 MHz with 8 Gbps effective speed. The power envelope confirms the intended use cases: 1000 W TDP for the MI350X versus 37 W for the integrated Arc part.

Head-to-Head Benchmarks

The database records no direct head-to-head benchmark entries between the AMD Instinct MI350X and Intel Arc 130V Mobile. Both products hold a 50th percentile position among all GPUs in the database, and both have an average benchmark score of 0. The winsA and winsB fields are each set to 0, indicating that no comparative testing data has been recorded. This absence of benchmark results means that the quantitative performance relationship between these two parts cannot be established from the recorded data.

What the data does allow is a comparison of theoretical throughput metrics derived from their specifications. The MI350X delivers 72.09 TFLOPS of FP32 compute and 72.09 TFLOPS of FP16 compute on a 1:1 ratio. The Arc 130V delivers 3.315 TFLOPS of FP32 and 6.630 TFLOPS of FP16 on a 2:1 ratio. The FP32 gap is substantial: the MI350X's figure is more than 21 times higher than the Arc 130V's. Texture rate follows a similar pattern, with the MI350X at 2,252.8 GTexel/s versus 103.6 GTexel/s for the Arc 130V. Pixel rate, however, tells the opposite story, as the MI350X reports 0 MPixel/s while the Arc 130V achieves 51.80 GPixel/s, a reflection of the MI350X's lack of rasterization hardware.

The memory bandwidth differential is the most extreme specification gap. The MI350X's 8.19 TB/s is orders of magnitude beyond the system dependent bandwidth of the Arc 130V. The MI350X's 288 GB of HBM3e capacity also dwarfs whatever system memory the Arc 130V might share. These are not competing products in any practical sense, and the benchmark data confirms this by listing no comparison points. The percentile ranking of 50 for both parts should not be read as performance equivalence; it simply reflects that neither has recorded benchmark scores in the database.

Specification Differences

The two products differ across nearly every recorded specification field. The MI350X uses a PCIe 5.0 x16 bus interface, while the Arc 130V uses IGP. The MI350X has no power connectors, while the Arc 130V lists no power connector data. The MI350X has no display outputs; the Arc 130V's display outputs are Portable Device Dependent. The MI350X is an OAM Module in slot width, whereas the Arc 130V is an IGP. The MI350X's dimensions are 102 mm in length and 165 mm in width, while the Arc 130V has no recorded dimensions.

Production status differs as well: the MI350X has no production status listed, while the Arc 130V is marked as Active. The MI350X's predecessor is Radeon Instinct, and the Arc 130V's predecessor is HD Graphics-M. Neither product has a listed successor. Release dates are separated by roughly nine months, with the Arc 130V launching on 2024-09-23 and the MI350X on 2025-06-11. Neither product has a launch MSRP in the database.

Compute resources show the largest structural difference. The MI350X has 16,384 shading units, 1024 TMUs, and 0 ROPs. The Arc 130V has 896 shading units, 56 TMUs, and 28 ROPs. The MI350X has no ray tracing cores, while the Arc 130V has 7. The MI350X's FP32 output is 72.09 TFLOPS, and its FP16 output is 72.09 TFLOPS at a 1:1 ratio. The Arc 130V's FP32 output is 3.315 TFLOPS, and its FP16 output is 6.630 TFLOPS at a 2:1 ratio. The MI350X's texture rate is 2,252.8 GTexel/s, and its pixel rate is 0 MPixel/s. The Arc 130V's texture rate is 103.6 GTexel/s, and its pixel rate is 51.80 GPixel/s.

Power specifications are similarly divergent. The MI350X carries a 1000 W TDP and a suggested PSU of 1400 W. The Arc 130V carries a 37 W TDP with no suggested PSU. Clock speeds differ by a wide margin at the base level: 1000 MHz for the MI350X versus 300 MHz for the Arc 130V, with boosts of 2200 MHz and 1850 MHz respectively. Memory type, size, bus width, and bandwidth all differ categorically: HBM3e versus System Shared, 288 GB versus System Shared, 8192 bit versus System Shared, and 8.19 TB/s versus System Dependent.

The Verdict

The recorded data describes two products with no benchmark overlap and no shared use cases. The AMD Instinct MI350X is a 1000 W OAM module with 288 GB of HBM3e memory, 16,384 shading units, and 72.09 TFLOPS of FP32 throughput. It has no display outputs, no raster pipeline, and no consumer API support. The Intel Arc 130V Mobile is a 37 W integrated GPU with 896 shading units, 7 ray tracing cores, and support for DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4. It uses system shared memory and delivers 3.315 TFLOPS of FP32 compute.

For workloads that require massive memory bandwidth, the MI350X's 8.19 TB/s and 288 GB capacity are the defining attributes. For client-side graphics and rendering, the Arc 130V's 51.80 GPixel/s pixel rate and ray tracing support are functional necessities that the MI350X lacks entirely. The MI350X's 72.09 TFLOPS FP32 figure and 2,252.8 GTexel/s texture rate indicate a device built for dense compute operations, not for generating frames. The Arc 130V's 6.630 TFLOPS FP16 output at a 2:1 ratio and 103.6 GTexel/s texture rate indicate a device designed for power-constrained, portable graphics.

The MI350X's transistor density of 77.7M per mm² on a 2380 mm² die reflects a design prioritizing raw throughput over efficiency. The Arc 130V's 172 mm² die with an unknown transistor count reflects an integration strategy prioritizing low power and physical compactness. The MI350X requires a 1400 W suggested PSU, while the Arc 130V operates within a 37 W envelope. Neither product's benchmark scores are recorded, so the 50th percentile ranking for both is a placeholder rather than a performance statement.

Selection between these two parts is dictated entirely by system role. The MI350X is appropriate for server or accelerator contexts where 1000 W power draw, OAM module mounting, and PCIe 5.0 x16 connectivity are acceptable. The Arc 130V is appropriate for mobile or embedded contexts where the IGP bus interface, system shared memory, and 37 W TDP are mandatory constraints. The database shows no overlap in their specification sets beyond the shared 3 nm TSMC process node, and no benchmark data exists to suggest any performance equivalence. The MI350X wins on every compute and memory metric. The Arc 130V wins on every graphics and integration metric. The verdict, strictly from the data, is that these products should not be compared for the same workload.