AMD Steam Machine GPU vs Intel Arc Graphics 128EU Mobile Comparison

The AMD Steam Machine GPU and Intel Arc Graphics 128EU Mobile occupy very different corners of the graphics hardware landscape. The AMD part is a discrete console-oriented component built on a modern 6 nm process with a substantial 13,300 million transistor count, while the Intel part is an integrated graphics solution for mobile processors, fabricated on a 10 nm node by Intel. The recorded data shows two designs with divergent goals: raw throughput and dedicated memory on the AMD side, power efficiency and system integration on the Intel side. This analysis relies solely on the specifications and benchmark information contained in the database, without reference to external testing or unlisted figures.

Where Each One Wins

The AMD Steam Machine GPU wins decisively in scenarios that demand high compute throughput and fast dedicated memory access. Its 17.56 TFLOPS of FP32 performance dwarfs the Intel part’s 4.608 TFLOPS, making the AMD component roughly 3.8 times faster in single-precision floating-point workloads. This advantage extends to texture and pixel processing as well. The AMD GPU delivers 274.4 GTexel/s of texture fill rate and 156.8 GPixel/s of pixel fill rate, compared to 144.0 GTexel/s and 72.00 GPixel/s for the Intel Arc Graphics 128EU Mobile. Applications that are fill-rate bound, such as high-resolution rendering with complex textures, will show a clear preference for the AMD part. The dedicated 8 GB of GDDR6 memory on a 128-bit bus provides 288.0 GB/s of bandwidth, whereas the Intel part relies on system shared memory with bandwidth described as system dependent. Workloads that stream large amounts of data, such as high-detail game assets or compute kernels with large working sets, benefit from the AMD GPU’s predictable, high-bandwidth memory subsystem.

The Intel Arc Graphics 128EU Mobile wins in power efficiency and integration. Its 28 W TDP is dramatically lower than the AMD GPU’s 110 W TDP, a difference that matters for thin-and-light mobile designs. The Intel part uses the system’s shared memory, eliminating the need for discrete VRAM and simplifying board design. Its 300 MHz base clock and 2250 MHz boost clock show a power-conscious operating range. The Intel part also uses a Ring Bus interface, which suits its integrated nature. For workloads that are lightly threaded or that do not saturate memory bandwidth, the Intel GPU can deliver adequate performance while consuming less than one-third of the AMD part’s power budget. The database also shows the Intel part reaches a higher FP16 rate of 9.216 TFLOPS due to a 2:1 ratio, effectively doubling its FP16 throughput relative to its FP32 figure, whereas the AMD GPU offers FP16 at a 1:1 ratio matching its 17.56 TFLOPS FP32 count. In mixed-precision scenarios where FP16 is acceptable, the Intel part’s relative efficiency improves, though the AMD GPU still leads in absolute FP16 throughput.

Architecture Differences

The two GPUs come from different architectural lineages. The AMD Steam Machine GPU uses RDNA 3.0 architecture on a 6 nm TSMC process, with the Navi 33 chip and the codename Hotpink Bonefish. It belongs to the Console GPU (Valve) generation. The Intel Arc Graphics 128EU Mobile uses Xe-LPG architecture on a 10 nm Intel process, with the Meteor Lake chip, and belongs to the Arc Graphics-M (Meteor Lake) generation. These architectural differences manifest in several measurable ways.

The compute resources differ substantially. The AMD GPU contains 1792 shading units, 112 texture mapping units, and 64 render output units, along with 28 ray tracing cores. The Intel GPU contains 1024 shading units, 64 texture mapping units, and 32 render output units, with no ray tracing cores listed in the database. The absence of RT cores on the Intel part means hardware-accelerated ray tracing is not available, while the AMD part includes dedicated hardware for that purpose. The AMD GPU’s transistor density is 65.2 million transistors per square millimeter, derived from its 13,300 million transistors on a 204 mm² die. The Intel part’s transistor count and die size are not recorded in the database, so no density comparison is possible.

Memory architecture also separates the two. The AMD GPU uses 8 GB of GDDR6 memory with a 128-bit bus and 288.0 GB/s of bandwidth. The Intel GPU uses system shared memory with a system dependent bus width and system dependent bandwidth. This means the AMD GPU’s memory performance is fixed and guaranteed, while the Intel GPU’s memory performance varies with the host system’s memory configuration. The AMD GPU has a game clock of 2250 MHz and a memory clock of 2250 MHz with 18 Gbps effective data rate, while the Intel part lists no game clock and no dedicated memory clock.

The API support shows a key difference. The AMD GPU supports DirectX 12 Ultimate with feature level 12_2, while the Intel GPU supports DirectX 12 with feature level 12_1. Both support OpenGL 4.6 and Vulkan 1.4. The DirectX 12 Ultimate designation on the AMD part indicates support for the full set of DirectX 12 Ultimate features, which typically includes hardware ray tracing and mesh shaders, among others. The Intel part’s DirectX 12_1 feature level does not include those same features. The AMD GPU also lists specific display outputs of 1x HDMI 2.1a and 1x DisplayPort 2.1, while the Intel part lists portable device dependent outputs, reflecting its integrated nature.

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark entries for these two GPUs, and the wins count for each is zero. However, the recorded specification data allows for a quantitative comparison of their theoretical performance limits. The most significant gap appears in FP32 compute. The AMD Steam Machine GPU delivers 17.56 TFLOPS, which is 3.81 times the Intel Arc Graphics 128EU Mobile’s 4.608 TFLOPS. This means the AMD part is 281% faster in single-precision floating-point throughput. For game workloads and compute tasks that rely on FP32, this difference is substantial.

Texture fill rate shows a smaller but still decisive gap. The AMD GPU produces 274.4 GTexel/s versus the Intel GPU’s 144.0 GTexel/s, a 90.6% advantage for the AMD part. Pixel fill rate similarly favors AMD: 156.8 GPixel/s versus 72.00 GPixel/s, a 117.8% advantage. These fill-rate figures directly affect rendering performance at high resolutions and with heavy texture usage.

Memory bandwidth presents one of the most consequential differences. The AMD GPU’s 288.0 GB/s of dedicated GDDR6 bandwidth is fixed, while the Intel GPU’s bandwidth is system dependent and not quantified in the database. In any scenario where dedicated bandwidth matters, the AMD GPU has a clear structural advantage. The Intel GPU’s shared memory approach means its effective bandwidth depends entirely on the host platform, introducing variability that the AMD GPU does not face.

The FP16 comparison adds nuance. The AMD GPU offers 17.56 TFLOPS of FP16 at a 1:1 ratio with its FP32 rate. The Intel GPU offers 9.216 TFLOPS of FP16 at a 2:1 ratio, meaning its FP16 throughput is double its FP32 throughput. In absolute terms, the AMD GPU still leads by 90.6% in FP16. However, the Intel part’s 2:1 ratio suggests a design that can more efficiently exploit FP16 workloads relative to its own FP32 capability. For applications that can use FP16 arithmetic, the Intel part closes some of the gap, though it does not erase it.

Clock speeds tell a story of two operating strategies. The AMD GPU has a base clock of 1720 MHz, a game clock of 2250 MHz, and a boost clock of 2450 MHz. The Intel GPU has a base clock of 300 MHz and a boost clock of 2250 MHz. The AMD part operates at a much higher base frequency, indicating it is designed to run at high sustained performance levels. The Intel part’s very low base clock of 300 MHz suggests aggressive power management, ramping up to 2250 MHz only when needed and when thermal and power budgets allow. The power envelopes confirm this: 110 W for AMD versus 28 W for Intel.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The AMD Steam Machine GPU delivers 17.56 TFLOPS of FP32, which is 3.81 times the Intel Arc Graphics 128EU Mobile’s 4.608 TFLOPS.

Q: What are the memory configurations of the two GPUs?

A: The AMD GPU uses 8 GB of GDDR6 memory on a 128-bit bus with 288.0 GB/s of bandwidth. The Intel GPU uses system shared memory with system dependent bus width and bandwidth.

Q: Do both GPUs support hardware ray tracing?

A: The AMD GPU includes 28 ray tracing cores. The Intel GPU lists no ray tracing cores in the database.

Q: What are the power consumption figures?

A: The AMD Steam Machine GPU has a TDP of 110 W. The Intel Arc Graphics 128EU Mobile has a TDP of 28 W.

Q: What DirectX versions do the two GPUs support?

A: The AMD GPU supports DirectX 12 Ultimate with feature level 12_2. The Intel GPU supports DirectX 12 with feature level 12_1. Both support OpenGL 4.6 and Vulkan 1.4.

Q: What process nodes are used for each GPU?

A: The AMD GPU uses a 6 nm TSMC process. The Intel GPU uses a 10 nm Intel process.

Specification Differences

The following table summarizes the fields where the two GPUs differ according to the database records.

| Specification | AMD Steam Machine GPU | Intel Arc Graphics 128EU Mobile |

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

| Architecture | RDNA 3.0 | Xe-LPG |

| Codename | Hotpink Bonefish | Not recorded |

| Generation | Console GPU (Valve) | Arc Graphics-M (Meteor Lake) |

| Process Node | 6 nm | 10 nm |

| Foundry | TSMC | Intel |

| Transistors | 13,300 million | Not recorded |

| Die Size | 204 mm² | Not recorded |

| Transistor Density | 65.2M / mm² | Not recorded |

| Base Clock | 1720 MHz | 300 MHz |

| Boost Clock | 2450 MHz | 2250 MHz |

| Game Clock | 2250 MHz | Not recorded |

| Memory Clock | 2250 MHz, 18 Gbps effective | System Shared |

| Memory Size | 8 GB | System Shared |

| Memory Type | GDDR6 | System Shared |

| Memory Bus Width | 128 bit | System Shared |

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

| Shading Units | 1792 | 1024 |

| Texture Mapping Units | 112 | 64 |

| Render Output Units | 64 | 32 |

| Ray Tracing Cores | 28 | Not recorded |

| Pixel Rate | 156.8 GPixel/s | 72.00 GPixel/s |

| Texture Rate | 274.4 GTexel/s | 144.0 GTexel/s |

| FP32 | 17.56 TFLOPS | 4.608 TFLOPS |

| FP16 | 17.56 TFLOPS (1:1) | 9.216 TFLOPS (2:1) |

| TDP | 110 W | 28 W |

| Slot Width | Not recorded | IGP |

| Power Connectors | None | Not recorded |

| Bus Interface | Not recorded | Ring Bus |

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

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

| Release Date | 2026-06-28 | 2023-12-13 |

| Predecessor | Not recorded | HD Graphics-M |

| Dimensions | 156 mm length, 152 mm height, 162 mm width | Not recorded |

The release dates show the AMD Steam Machine GPU is a 2026 product, while the Intel Arc Graphics 128EU Mobile dates to December 2023. The AMD part is a discrete component with its own board dimensions and power connector requirements of none, while the Intel part is an integrated GPU (IGP) that relies on the host system for power and display. The AMD part’s production status is active, and the Intel part’s production status is also active. Both GPUs sit at the 50th percentile in the database’s all-GPU ranking, though this percentile is based on the recorded benchmark scores, which are zero for both parts in the current data set. The nearest rivals lists are empty for both GPUs, so no direct comparative percentile deltas are available. The data as recorded presents a clear picture: the AMD Steam Machine GPU is a high-throughput discrete solution for console-class gaming, and the Intel Arc Graphics 128EU Mobile is a power-efficient integrated solution for mobile systems. Each wins in its intended domain, and the specification differences reinforce that separation.