AMD Radeon AI PRO 9600D vs Intel Arc 130T Mobile Comparison

The Verdict

The database records two very different mobile and desktop compute solutions. The AMD Radeon AI PRO 9600D is a discrete, single-slot accelerator built on the Navi 48 chip with RDNA 4.0 architecture. The Intel Arc 130T Mobile is an integrated graphics processor embedded in the Arrow Lake-H chip using Xe-LPG+ architecture. The recorded data shows a stark performance hierarchy: the AMD part delivers 24.82 TFLOPS FP32 compute, while the Intel part delivers 3.942 TFLOPS FP32. That is a 6.3x gap in raw floating-point throughput. The AMD card also has 32 GB of dedicated GDDR6 memory on a 256-bit bus with 576.0 GB/s bandwidth, whereas the Intel part uses System Shared memory with system-dependent bandwidth.

For workloads that demand heavy compute, large memory capacity, and sustained throughput, the AMD Radeon AI PRO 9600D is the only choice in this comparison. For power-constrained systems where integrated graphics suffice, the Intel Arc 130T Mobile fits a 35 W envelope. The data does not support any scenario where the Intel part outperforms the AMD part in raw GPU metrics. Both parts sit at the 50th percentile against all GPUs in the database, and both have an average benchmark score of zero, meaning no direct recorded benchmark comparisons exist. The verdict is therefore driven entirely by specification analysis: the AMD part is for dedicated compute and rendering workloads, the Intel part is for basic graphics in a mobile platform.

Architecture Differences

The AMD Radeon AI PRO 9600D uses the Navi 48 chip built on TSMC's 4 nm process. The Intel Arc 130T Mobile uses the Arrow Lake-H chip built on TSMC's 5 nm process. The process node difference is one generation apart in the recorded data, 4 nm versus 5 nm. AMD's architecture is RDNA 4.0, while Intel's is Xe-LPG+. The AMD chip integrates 53,900 million transistors on a 357 mm² die, giving a transistor density of 151.0M per mm². Intel's transistor count and die size are recorded as unknown, so no density comparison is possible.

The AMD part is a discrete accelerator with a 150 W TDP and a single-slot form factor. It requires a 1x 16-pin power connector and a 450 W suggested power supply. The Intel part is an IGP with a 35 W TDP and no power connector, no suggested PSU, and no slot width beyond "IGP". The bus interface differs fundamentally: PCIe 5.0 x16 for AMD versus IGP for Intel. The AMD card has a single DisplayPort 2.1a output, while the Intel part's display outputs are portable-device dependent.

The memory architecture is another major divergence. AMD uses 32 GB of GDDR6 on a 256-bit bus with 576.0 GB/s bandwidth. Intel uses System Shared memory, meaning the memory size, type, bus width, and bandwidth are all system dependent. The AMD memory clock is 2250 MHz (18 Gbps effective), while Intel's memory clock is listed as System Shared with no effective rate.

Compute resources differ by a wide margin. AMD has 3,072 shading units, 192 TMUs, 96 ROPs, and 48 ray-tracing cores. Intel has 896 shading units, 56 TMUs, 28 ROPs, and 7 ray-tracing cores. The AMD part has 3.4x the shading units, 3.4x the TMUs, 3.4x the ROPs, and 6.9x the ray-tracing cores.

Head-to-Head Benchmarks

No direct head-to-head benchmark results are recorded in the database. The head-to-head benchmark array is empty, and both parts show zero benchmark wins. The average benchmark score for both is zero, and the percentile rank against all GPUs is 50 for each. This means the database contains no measured performance deltas between these two products. The comparison must rely on the recorded specification data.

The FP32 compute figures provide the clearest measurable difference. AMD delivers 24.82 TFLOPS, Intel delivers 3.942 TFLOPS. The AMD part is 6.3x higher in FP32 throughput. The FP16 figures show a different ratio: AMD delivers 24.82 TFLOPS with a 1:1 ratio, Intel delivers 7.885 TFLOPS with a 2:1 ratio. In FP16, AMD is 3.1x higher. The pixel rate is 193.9 GPixel/s for AMD versus 61.60 GPixel/s for Intel, a 3.1x gap. The texture rate is 387.8 GTexel/s for AMD versus 123.2 GTexel/s for Intel, also a 3.1x gap.

Clock speeds tell a more complex story. AMD has a base clock of 1080 MHz and a boost clock of 2020 MHz. Intel has a base clock of 300 MHz and a boost clock of 2200 MHz. Intel's boost clock is 180 MHz higher, but its base clock is 780 MHz lower. The game clock for AMD is 1080 MHz; Intel has no recorded game clock. The higher Intel boost clock does not compensate for the much lower shading unit count, as the FP32 figures confirm.

Memory bandwidth is another decisive data point. AMD provides 576.0 GB/s of dedicated bandwidth. Intel's bandwidth is listed as System Dependent, which means it cannot be compared directly. The AMD memory bus is 256 bits wide, versus System Shared for Intel.

Specification Differences

The two parts differ in nearly every recorded specification field. The process node is 4 nm for AMD and 5 nm for Intel. The chip is Navi 48 for AMD and Arrow Lake-H for Intel. The architecture is RDNA 4.0 for AMD and Xe-LPG+ for Intel. AMD's generation is Radeon Pro Navi (Navi IV Series); Intel's is Arc Graphics-M (Arrow Lake). AMD's predecessor is Radeon Pro Vega; Intel's predecessor is HD Graphics-M.

The transistor count is 53,900 million for AMD and unknown for Intel. The die size is 357 mm² for AMD and unknown for Intel. The transistor density is 151.0M per mm² for AMD and null for Intel. The base clock is 1080 MHz for AMD and 300 MHz for Intel. The boost clock is 2020 MHz for AMD and 2200 MHz for Intel. The game clock is 1080 MHz for AMD and null for Intel. The memory clock is 2250 MHz (18 Gbps effective) for AMD and System Shared for Intel.

Memory size is 32 GB for AMD and System Shared for Intel. Memory type is GDDR6 for AMD and System Shared for Intel. Bus width is 256 bit for AMD and System Shared for Intel. Bandwidth is 576.0 GB/s for AMD and System Dependent for Intel. Shading units are 3,072 for AMD and 896 for Intel. TMUs are 192 for AMD and 56 for Intel. ROPs are 96 for AMD and 28 for Intel. Ray-tracing cores are 48 for AMD and 7 for Intel.

Pixel rate is 193.9 GPixel/s for AMD and 61.60 GPixel/s for Intel. Texture rate is 387.8 GTexel/s for AMD and 123.2 GTexel/s for Intel. FP32 is 24.82 TFLOPS for AMD and 3.942 TFLOPS for Intel. FP16 is 24.82 TFLOPS (1:1) for AMD and 7.885 TFLOPS (2:1) for Intel. TDP is 150 W for AMD and 35 W for Intel. Slot width is single-slot for AMD and IGP for Intel. Power connectors are 1x 16-pin for AMD and null for Intel. Suggested PSU is 450 W for AMD and null for Intel. Bus interface is PCIe 5.0 x16 for AMD and IGP for Intel.

Display outputs are 1x DisplayPort 2.1a for AMD and Portable Device Dependent for Intel. Dimensions are 241 mm length, 111 mm height, 19 mm width for AMD, and null for Intel. The release date is 2025-12-10 for AMD and 2025-01-12 for Intel. The AMD part is newer by roughly eleven months. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both have null tensor cores, and both have a null launch MSRP. Both are Active in production status.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The AMD Radeon AI PRO 9600D delivers 24.82 TFLOPS FP32, while the Intel Arc 130T Mobile delivers 3.942 TFLOPS. The AMD part is 6.3x higher in FP32 throughput.

Q: How much memory does each GPU have?

A: The AMD Radeon AI PRO 9600D has 32 GB of GDDR6 on a 256-bit bus with 576.0 GB/s bandwidth. The Intel Arc 130T Mobile uses System Shared memory, so its size, type, bus width, and bandwidth are system dependent.

Q: What are the power requirements for each GPU?

A: The AMD Radeon AI PRO 9600D has a 150 W TDP, uses a 1x 16-pin power connector, and has a 450 W suggested PSU. The Intel Arc 130T Mobile has a 35 W TDP, no power connector, and no suggested PSU.

Q: Which GPU has more ray-tracing cores?

A: The AMD Radeon AI PRO 9600D has 48 ray-tracing cores. The Intel Arc 130T Mobile has 7 ray-tracing cores. The AMD part has 6.9x more ray-tracing cores.

Q: Are there any recorded benchmark scores for these GPUs?

A: Both GPUs have an average benchmark score of zero in the database, and both sit at the 50th percentile against all GPUs. No head-to-head benchmark results are recorded.

Q: What is the process node for each GPU?

A: The AMD Radeon AI PRO 9600D uses a 4 nm process from TSMC. The Intel Arc 130T Mobile uses a 5 nm process from TSMC.

Where Each One Wins

The AMD Radeon AI PRO 9600D wins in every measurable GPU compute metric recorded in the database. It has 6.3x higher FP32 throughput, 3.1x higher FP16 throughput, 3.1x higher pixel rate, and 3.1x higher texture rate. It has 32 GB of dedicated GDDR6 memory with 576.0 GB/s bandwidth, which is a decisive advantage over System Shared memory. It has 3.4x more shading units, 3.4x more TMUs, 3.4x more ROPs, and 6.9x more ray-tracing cores. It uses a newer 4 nm process versus Intel's 5 nm process. It also has a higher base clock: 1080 MHz versus 300 MHz. The AMD part is a discrete PCIe 5.0 x16 card with a single DisplayPort 2.1a output, making it suitable for dedicated compute, rendering, and AI workloads where sustained throughput and large memory capacity are required.

The Intel Arc 130T Mobile wins in power efficiency and integration. Its 35 W TDP is 115 W lower than the AMD part's 150 W TDP. It requires no power connector and no suggested PSU, and it is an IGP with no slot width, meaning it fits directly into a mobile processor package. Its boost clock is higher at 2200 MHz versus 2020 MHz, though this does not translate into higher FP32 throughput. Its FP16 performance of 7.885 TFLOPS uses a 2:1 ratio, which means it can process FP16 at twice the rate of FP32, while AMD's FP16 runs at a 1:1 ratio. The Intel part is also older in the database, released on 2025-01-12 versus 2025-12-10 for AMD.

The use-case split is clear from the recorded data. The AMD Radeon AI PRO 9600D is for workloads that need high compute density, large dedicated memory, and discrete expansion: AI inference, rendering, and professional graphics. The Intel Arc 130T Mobile is for mobile platforms where the 35 W TDP and integrated form factor are the priority, and where the system-shared memory and lower compute throughput are acceptable. No benchmark data exists to refine this split further, so the specification differences are the only recorded basis for the verdict.