AMD Instinct MI350X vs Intel Arc 130T Mobile Comparison

Head-to-Head Benchmarks

The recorded database contains no direct benchmark scores for either the AMD Instinct MI350X or the Intel Arc 130T Mobile. Both entries show an average benchmark score of zero, and the head-to-head benchmark array is empty. Consequently, no exact performance deltas can be cited from direct comparisons. However, the specification data allows for a thorough analytical comparison based on theoretical throughput metrics, which are recorded in the database.

The most striking difference emerges in FP32 compute. The AMD Instinct MI350X delivers 72.09 TFLOPS of FP32 throughput, while the Intel Arc 130T Mobile delivers 3.942 TFLOPS. This represents a ratio of approximately 18.3 to 1 in favor of the AMD part. In FP16, the gap narrows slightly but remains enormous: the MI350X sustains 72.09 TFLOPS with a 1:1 ratio to FP32, whereas the Arc 130T reaches 7.885 TFLOPS using a 2:1 ratio. The AMD accelerator therefore provides 9.1 times the FP16 throughput of the Intel integrated GPU.

Texture rate tells a similar story. The MI350X processes 2,252.8 GTexel/s, compared to 123.2 GTexel/s for the Arc 130T. That is an 18.3-fold advantage in texture fillrate, consistent with the FP32 gap since both parts use the same ratio of texture mapping units to shader processors. Pixel rate, however, reverses direction in a surprising way. The Arc 130T records 61.60 GPixel/s, while the MI350X records 0 MPixel/s. The AMD accelerator has no raster output units, with an ROP count of zero, so it cannot generate traditional pixel output at all. The Intel part, with 28 ROPs, handles conventional rasterization tasks.

Both parts share a boost clock of 2200 MHz, which is the only clock speed they have in common. The MI350X has a base clock of 1000 MHz, while the Arc 130T has a base clock of 300 MHz. The AMD chip also runs its HBM3e memory at 2000 MHz with 8 Gbps effective transfer, while the Intel part uses system shared memory with no dedicated clock data. Memory bandwidth illustrates the scale difference: 8.19 TB/s for the MI350X versus "System Dependent" for the Arc 130T. The database lists no direct benchmark wins for either product, so all conclusions here derive from the recorded specification fields.

Architecture Differences

The AMD Instinct MI350X uses the CDNA 4.0 architecture, built on a 3 nm process at TSMC. It contains 185,000 million transistors on a 2380 mm² die, yielding a transistor density of 77.7 million transistors per square millimeter. The chip is designated as "MI350 256CU," indicating 256 compute units. The Intel Arc 130T Mobile uses the Xe-LPG+ architecture, built on a 5 nm process at TSMC. Its transistor count and die size are listed as unknown in the database. The chip is designated "Arrow Lake-H," and it belongs to the Arc Graphics-M generation.

The MI350X has 16,384 shading units, 1,024 texture mapping units, and zero ROPs. It also has no dedicated ray tracing cores listed and no tensor cores listed. The Arc 130T has 896 shading units, 56 TMUs, and 28 ROPs. It includes 7 ray tracing cores, while tensor core data is absent from its record. This structural difference explains the divergent pixel rates: a compute accelerator without ROPs cannot output pixels, whereas an integrated GPU with ROPs handles display output.

Memory architecture separates the two products categorically. The MI350X uses 288 GB of HBM3e memory across an 8192-bit bus, producing 8.19 TB/s of bandwidth. The Arc 130T uses "System Shared" memory, with type, bus width, and bandwidth all listed as system dependent. The AMD part operates as an OAM Module with no power connectors and a 1000 W TDP, requiring a suggested PSU of 1400 W. The Intel part is an IGP with a 35 W TDP, no separate power connectors, and no suggested PSU requirement.

API support differs completely. The MI350X lists DirectX, OpenGL, and Vulkan as "N/A," reflecting its server accelerator role with no display outputs. The Arc 130T supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Display outputs for the Intel part are "Portable Device Dependent," while the AMD part has no outputs at all. The bus interfaces also diverge: PCIe 5.0 x16 for the MI350X versus IGP for the Arc 130T.

Process node and manufacturing details reinforce the positioning. The MI350X uses a 3 nm node with a massive die and high transistor density. The Arc 130T uses a 5 nm node, though exact transistor and die measurements are not recorded. Release dates show the MI350X launched on June 11, 2025, while the Arc 130T launched on January 12, 2025. The predecessor fields also differ: "Radeon Instinct" for AMD and "HD Graphics-M" for Intel.

Where Each One Wins

The AMD Instinct MI350X wins decisively in raw compute throughput. Its 72.09 TFLOPS FP32 and FP16 performance, combined with 2,252.8 GTexel/s texture rate, makes it suitable for high-density numerical workloads. The 288 GB HBM3e capacity with 8.19 TB/s bandwidth supports large data sets that cannot fit in the system memory of a mobile part. The 1000 W TDP and OAM Module form factor indicate a data center installation context, with PCIe 5.0 x16 connectivity for server integration.

The Intel Arc 130T Mobile wins in conventional graphics output. Its 28 ROPs deliver 61.60 GPixel/s, which is the only pixel throughput recorded for either product. The 7 ray tracing cores provide hardware acceleration for ray-traced effects, a feature entirely absent from the MI350X record. The Arc 130T supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, making it functional for gaming and general-purpose graphics APIs. Its 35 W TDP fits within mobile power budgets, and its IGP bus interface requires no separate add-in card.

For FP16 workloads, the MI350X offers a 1:1 ratio, meaning it processes half-precision at the same rate as single-precision. The Arc 130T offers a 2:1 ratio, doubling its FP16 throughput relative to FP32, but even at 7.885 TFLOPS, it remains far below the AMD part. The database does not record tensor core counts for either product, so no comparison of AI-specific tensor performance can be made. The MI350X also has no display outputs, making it unsuitable for any task requiring visual output. The Arc 130T, with portable-device-dependent outputs, handles display duties in mobile systems.

The power envelope separates use cases further. The MI350X requires a 1400 W suggested PSU and has no power connectors on the module itself, indicating a system-level power delivery design. The Arc 130T draws 35 W and needs no additional power connectors. These figures come directly from the database records.

FAQ

Q: Which product has higher FP32 performance?

A: The AMD Instinct MI350X records 72.09 TFLOPS FP32, while the Intel Arc 130T Mobile records 3.942 TFLOPS. The AMD part has roughly 18 times the FP32 throughput.

Q: Does the AMD Instinct MI350X support any display outputs?

A: No. The database lists "No outputs" for display outputs, and its pixel rate is 0 MPixel/s with zero ROPs. It is not designed for graphics output.

Q: What ray tracing capabilities does the Intel Arc 130T Mobile have?

A: The Arc 130T has 7 ray tracing cores. The MI350X has no ray tracing cores listed in its record.

Q: What memory configurations are recorded for each product?

A: The MI350X has 288 GB of HBM3e memory on an 8192-bit bus with 8.19 TB/s bandwidth. The Arc 130T uses System Shared memory, with system-dependent type, bus width, and bandwidth.

Q: What API support is listed for each product?

A: The MI350X lists DirectX, OpenGL, and Vulkan as N/A. The Arc 130T lists DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What are the power requirements according to the database?

A: The MI350X has a TDP of 1000 W with a suggested PSU of 1400 W. The Arc 130T has a TDP of 35 W with no suggested PSU listed.

Specification Differences

The database records several fields where the two products differ:

• Architecture: CDNA 4.0 (MI350X) versus Xe-LPG+ (Arc 130T)
• Generation: Instinct (MIx) versus Arc Graphics-M (Arrow Lake)
• Process Node: 3 nm versus 5 nm
• Transistors: 185,000 million versus unknown
• Die Size: 2380 mm² versus unknown
• Transistor Density: 77.7M / mm² versus not listed
• Base Clock: 1000 MHz versus 300 MHz
• Boost Clock: 2200 MHz for both (no difference)
• Memory Clock: 2000 MHz 8 Gbps effective versus System Shared
• Memory Size: 288 GB versus System Shared
• Memory Type: HBM3e versus System Shared
• Memory Bus Width: 8192 bit versus System Shared
• Memory Bandwidth: 8.19 TB/s versus System Dependent
• Shading Units: 16,384 versus 896
• TMUs: 1,024 versus 56
• ROPs: 0 versus 28
• RT Cores: not listed versus 7
• Pixel Rate: 0 MPixel/s versus 61.60 GPixel/s
• Texture Rate: 2,252.8 GTexel/s versus 123.2 GTexel/s
• FP32: 72.09 TFLOPS versus 3.942 TFLOPS
• FP16: 72.09 TFLOPS (1:1) versus 7.885 TFLOPS (2:1)
• TDP: 1000 W versus 35 W
• Slot Width: OAM Module versus IGP
• Power Connectors: None versus not listed
• Suggested PSU: 1400 W versus not listed
• Bus Interface: PCIe 5.0 x16 versus IGP
• Display Outputs: No outputs versus Portable Device Dependent
• DirectX: N/A versus 12 Ultimate (12_2)
• OpenGL: N/A versus 4.6
• Vulkan: N/A versus 1.4
• Dimensions: 102 mm length, 165 mm width versus not listed
• Production Status: not listed versus Active
• Release Date: June 11, 2025 versus January 12, 2025
• Predecessor: Radeon Instinct versus HD Graphics-M

The launch MSRP is not recorded for either product, so no price information can be stated.

The Verdict

The recorded data points to two products with fundamentally different purposes. The AMD Instinct MI350X is a data center compute accelerator with massive FP32 and FP16 throughput, 288 GB of HBM3e memory, and no graphics output capability. The Intel Arc 130T Mobile is an integrated GPU for mobile systems, with conventional rasterization hardware, ray tracing cores, and full graphics API support.

For workloads that demand raw floating-point throughput, memory capacity, or memory bandwidth, the MI350X is the clear choice based on the numbers. Its 72.09 TFLOPS FP32 and 8.19 TB/s bandwidth dwarf the Arc 130T's 3.942 TFLOPS and system-dependent bandwidth. The 288 GB memory capacity supports data sets that no integrated GPU can approach. The 1000 W TDP and OAM Module form factor place it in server racks, not laptops.

For tasks that require pixel output, ray tracing, or standard graphics APIs, the Arc 130T is the only viable option from these two. It has 28 ROPs and 61.60 GPixel/s pixel rate, while the MI350X has zero. It supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, whereas the MI350X lists N/A for all three. Its 35 W TDP fits mobile power constraints, and its IGP bus interface requires no expansion slot.

The percentile scores are identical at 50 for both products, but this reflects the absence of benchmark data rather than comparable performance. With no average benchmark scores and no nearest rivals listed, the database provides no direct performance ranking. The specification analysis shows the MI350X excels in compute density and memory throughput, while the Arc 130T excels in graphics output and API compatibility. Each product wins in its respective domain, and neither can substitute for the other in the workloads where the other is strong.