AMD Steam Machine GPU vs Intel Arc 130T Mobile Comparison

Head-to-Head Benchmarks

The recorded data contains no direct benchmark scores for either GPU, so the comparison must be built from the specification differences and the performance indicators each unit carries. The AMD Steam Machine GPU reports a raw FP32 throughput of 17.56 TFLOPS, while the Intel Arc 130T Mobile delivers 3.942 TFLOPS. That is a 4.45x gap in raw compute, which translates into a substantial advantage for AMD in any shader-bound workload. The pixel rate tells a similar story: AMD outputs 156.8 GPixel/s against Intel's 61.60 GPixel/s, a 2.55x difference. Texture rate follows with AMD at 274.4 GTexel/s versus Intel's 123.2 GTexel/s, a 2.23x edge. These three figures alone indicate that the AMD part is built for sustained rendering throughput, while the Intel part is optimized for efficiency within a much lower power envelope.

FP16 performance adds nuance. AMD lists 17.56 TFLOPS for FP16 with a 1:1 ratio, meaning no dedicated half-precision acceleration. Intel shows 7.885 TFLOPS with a 2:1 ratio, indicating that the Arc 130T can double its FP32 rate when operating on FP16 data. In workloads that leverage FP16, Intel's relative standing improves, but it still trails AMD's raw FP16 output by a factor of 2.23. For AI inference or compute tasks that use half precision, the Intel part is more competitive than its FP32 numbers suggest, but it remains clearly behind.

Both GPUs support DirectX 12 Ultimate with feature level 12_2, OpenGL 4.6, and Vulkan 1.4. That means either unit can run modern titles with ray tracing and mesh shaders at the API level. The AMD part has 28 ray tracing cores, while the Intel part has 7. The RT core count difference of 4x mirrors the shading unit difference: AMD has 1792 shading units against Intel's 896, exactly double. The AMD part also has 112 texture mapping units and 64 ROPs, versus 56 TMUs and 28 ROPs on the Intel side. Every internal resource on the AMD GPU is larger, often by a factor of 2 or more.

Memory bandwidth is where the two diverge most sharply. AMD uses 8 GB of GDDR6 on a 128-bit bus with 288.0 GB/s of bandwidth. Intel uses system shared memory with bandwidth listed as system dependent. That means the Intel GPU must compete with the CPU for memory access, and its effective bandwidth will vary with the host platform. The AMD part has a fixed, dedicated pool of fast VRAM, which is a hard advantage for texture streaming, high-resolution rendering, and any data-intensive workload. The Intel part's shared memory approach keeps costs and power low, but it cannot match the sustained throughput of dedicated GDDR6.

In the absence of direct head-to-head benchmark results, the specification sheet is the only measurable basis for comparison. The data shows AMD winning every throughput metric, often by a wide margin. The Intel part wins on power efficiency, with a 35 W TDP against AMD's 110 W, and on physical integration, since it is an IGP with no separate card footprint. The choice between them is not about equal performance; it is about what the host system needs.

FAQ

Q: Which GPU has higher raw compute throughput?

A: The AMD Steam Machine GPU delivers 17.56 TFLOPS of FP32 compute, while the Intel Arc 130T Mobile delivers 3.942 TFLOPS. AMD is 4.45x faster in FP32.

Q: How do the memory systems compare?

A: AMD uses 8 GB of GDDR6 on a 128-bit bus with 288.0 GB/s of dedicated bandwidth. Intel uses system shared memory, with bandwidth that is system dependent and shared with the CPU.

Q: Do both GPUs support the same graphics APIs?

A: Yes. Both list DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. This means both are capable of modern rendering features like ray tracing and mesh shaders.

Q: What is the power draw difference?

A: The AMD Steam Machine GPU has a TDP of 110 W, while the Intel Arc 130T Mobile has a TDP of 35 W. Intel draws roughly one third of AMD's power budget.

Q: Which GPU has more ray tracing cores?

A: The AMD Steam Machine GPU has 28 ray tracing cores. The Intel Arc 130T Mobile has 7 ray tracing cores, exactly one quarter of AMD's count.

Q: Is the Intel part a discrete card or an integrated solution?

A: The Intel Arc 130T Mobile is an IGP with a bus interface of IGP and no slot width, meaning it is integrated into the processor package. The AMD Steam Machine GPU is a discrete console GPU with a 156 mm length, 152 mm height, and 162 mm width.

Architecture Differences

The AMD Steam Machine GPU uses the Navi 33 chip built on the RDNA 3.0 architecture, with the codename Hotpink Bonefish. It is a discrete console GPU designed for Valve's Steam Machine platform, fabricated on a 6 nm process at TSMC. The chip contains 13,300 million transistors on a 204 mm² die, which yields a transistor density of 65.2M per mm². This is a large, high-throughput design with dedicated VRAM and a full complement of fixed-function units.

The Intel Arc 130T Mobile uses the Arrow Lake-H chip built on the Xe-LPG+ architecture, part of the Arc Graphics-M generation for Arrow Lake processors. It is fabricated on a 5 nm process at TSMC, but its transistor count and die size are unknown. The architecture is designed for integration into mobile processors, as evidenced by the IGP bus interface and the system shared memory. The Xe-LPG+ architecture is a derivative of Intel's Xe-LPG line, optimized for low power and compact footprints.

The architectural philosophies are direct opposites. AMD's RDNA 3.0 is a high-performance graphics architecture with a wide 128-bit memory bus and a massive shader array. Intel's Xe-LPG+ is a power-scaled architecture that relies on shared system memory and a much smaller execution resource pool. The AMD part has 1792 shading units, 112 TMUs, 64 ROPs, and 28 RT cores. The Intel part has 896 shading units, 56 TMUs, 28 ROPs, and 7 RT cores. Each AMD resource count is exactly double or quadruple the Intel equivalent, which explains the large performance gap in throughput metrics.

FP16 handling differs as well. AMD reports FP16 at 17.56 TFLOPS with a 1:1 ratio, meaning the FP32 and FP16 pipelines are the same width. Intel reports FP16 at 7.885 TFLOPS with a 2:1 ratio, meaning the FP16 pipeline can process twice as many operations per clock as the FP32 pipeline. This gives Intel a relative advantage in half-precision compute, even though AMD's absolute FP16 output is still higher.

The memory architecture is another major split. AMD uses dedicated GDDR6 with a fixed bandwidth of 288.0 GB/s. Intel uses system shared memory, which means the GPU has no dedicated VRAM and must rely on the host's RAM. The bandwidth for Intel is system dependent, so it varies with the platform. The AMD design guarantees consistent memory performance, while the Intel design trades that consistency for lower cost and power.

Specification Differences

| Specification | AMD Steam Machine GPU | Intel Arc 130T Mobile |

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

| Chip | Navi 33 | Arrow Lake-H |

| Architecture | RDNA 3.0 | Xe-LPG+ |

| Process Node | 6 nm | 5 nm |

| Transistors | 13,300 million | unknown |

| Die Size | 204 mm² | unknown |

| Base Clock | 1720 MHz | 300 MHz |

| Boost Clock | 2450 MHz | 2200 MHz |

| Game Clock | 2250 MHz | null |

| Memory Size | 8 GB | System Shared |

| Memory Type | GDDR6 | System Shared |

| Memory Bus | 128 bit | System Shared |

| Memory Bandwidth | 288.0 GB/s | System Dependent |

| Shading Units | 1792 | 896 |

| TMUs | 112 | 56 |

| ROPs | 64 | 28 |

| RT Cores | 28 | 7 |

| Pixel Rate | 156.8 GPixel/s | 61.60 GPixel/s |

| Texture Rate | 274.4 GTexel/s | 123.2 GTexel/s |

| FP32 | 17.56 TFLOPS | 3.942 TFLOPS |

| FP16 | 17.56 TFLOPS (1:1) | 7.885 TFLOPS (2:1) |

| TDP | 110 W | 35 W |

| Bus Interface | null | IGP |

| Display Outputs | 1x HDMI 2.1, 1x DisplayPort 2.1 | Portable Device Dependent |

| Dimensions | 156 mm x 152 mm x 162 mm | null |

| Release Date | 2026-06-28 | 2025-01-12 |

The AMD part has a higher base clock (1720 MHz vs 300 MHz) and a higher boost clock (2450 MHz vs 2200 MHz). The Intel part's 300 MHz base clock is extremely low, indicating that it spends most of its time in idle or low-power states and only ramps up under load. The AMD part also has a defined game clock of 2250 MHz, which is a sustained frequency target for gaming workloads.

The AMD part uses a discrete card form factor with physical dimensions of 156 mm by 152 mm by 162 mm. The Intel part has no dimensions listed because it is an IGP integrated into the processor. The AMD part has no power connectors listed, while the Intel part has null power connectors due to its integrated nature. The Intel part's display outputs are portable device dependent, meaning they vary with the laptop or handheld it is installed in.

Both parts are marked as Active in production status. The Intel part has a predecessor listed as HD Graphics-M, while the AMD part has no predecessor or successor. The release dates differ by roughly a year and a half, with Intel launching in January 2025 and AMD launching in June 2026.

Where Each One Wins

The AMD Steam Machine GPU wins every raw performance category in the recorded data. It has 4.45x the FP32 throughput, 2.55x the pixel rate, 2.23x the texture rate, and 4x the ray tracing cores compared to the Intel Arc 130T Mobile. It also has dedicated GDDR6 memory with 288.0 GB/s of bandwidth, which is a fixed resource that does not depend on the host system. For any workload that stresses the GPU, such as high-resolution gaming, 3D rendering, or compute-heavy applications, the AMD part is the clear performer.

The Intel Arc 130T Mobile wins on power efficiency and integration. Its TDP of 35 W is less than one third of AMD's 110 W, making it suitable for thin-and-light laptops, handhelds, and other portable devices where battery life and thermals are critical. Its IGP bus interface means it requires no separate card slot, no additional power connectors, and no extra physical space. The system shared memory approach also means there is no dedicated VRAM cost, which keeps the overall system simpler and cheaper to manufacture.

The Intel part also wins on FP16 efficiency relative to its FP32 output. With a 2:1 ratio, it can process half-precision data at 7.885 TFLOPS, which is double its FP32 rate. This makes it more competitive in AI inference and certain compute workloads that use FP16, even though AMD's absolute FP16 output of 17.56 TFLOPS is still higher. The Intel part's lower base clock of 300 MHz also suggests better idle power characteristics, which is a meaningful advantage in battery-powered devices.

For gaming, the AMD part is the only realistic choice for demanding titles. Its dedicated 8 GB of GDDR6 and 288.0 GB/s bandwidth ensure that textures and geometry load without stutter, while its 28 RT cores provide hardware ray tracing capability that is 4x denser than Intel's. The Intel part can handle lighter games and esports titles, but its shared memory and lower throughput will limit it at higher resolutions and detail settings.

The Verdict

The recorded data shows two GPUs with opposite design goals. The AMD Steam Machine GPU is a high-performance discrete part built for a dedicated console platform. It delivers 17.56 TFLOPS of FP32 compute, 288.0 GB/s of dedicated memory bandwidth, and a full set of rendering resources that are 2x to 4x larger than Intel's. Its 110 W TDP and 156 mm by 152 mm by 162 mm footprint indicate that it is meant to sit inside a stationary console or desktop-style chassis, not a portable device.

The Intel Arc 130T Mobile is an integrated GPU for mobile processors. It draws 35 W, uses system shared memory, and has no physical dimensions because it is embedded in the CPU package. Its 3.942 TFLOPS of FP32 compute and 7 RT cores are sufficient for basic 3D acceleration and light gaming, but they cannot match the AMD part in any throughput metric.

Who should pick which depends entirely on the host system. The AMD Steam Machine GPU is for a device that prioritizes graphical performance over power draw and physical space. The Intel Arc 130T Mobile is for a device that prioritizes portability, battery life, and integration simplicity. There is no overlap in their intended use cases, and the data reflects that split clearly. Buyers seeking maximum frame rates and visual fidelity should choose the AMD part. Buyers seeking a compact, low-power integrated solution should choose the Intel part.