AMD Steam Machine GPU vs NVIDIA GeForce RTX 5090 Mobile Comparison

Where Each One Wins

The recorded data splits these two GPUs into entirely different performance classes. The AMD Steam Machine GPU has no benchmark entries in the database, which means every measurable win belongs to the NVIDIA GeForce RTX 5090 Mobile. The RTX 5090 Mobile posts a PassMark G3D score of 30034, a Geekbench OpenCL score of 201834, and a Geekbench Vulkan score of 198405. Its average benchmark score sits at 45152, placing it in the 84th percentile of all GPUs tracked by the database. The AMD part holds the 50th percentile with an average score of zero, reflecting the absence of recorded benchmark runs.

The RTX 5090 Mobile also wins in compute-oriented workloads. PassMark GPU Compute returns 13401, while DirectX 12 performance in PassMark reaches 138. DirectX 11 scores 269, DirectX 10 scores 183, and DirectX 9 scores 324. The 2D portion of PassMark yields 1057. These figures establish a broad sweep across API generations and compute tasks. The AMD Steam Machine GPU cannot claim a single recorded victory, so any use-case split must be inferred from architectural differences rather than measured outcomes.

The nearest rivals for the RTX 5090 Mobile provide context for its standing. The AMD Radeon Pro 5500 XT averages 45384, which is 0.5% higher than the RTX 5090 Mobile. The Intel Arc A730M averages 45592, 1% higher. The NVIDIA RTX 5880 Ada Generation averages 45972, 1.8% higher. The NVIDIA GeForce RTX 4070 Ti averages 44795, 0.8% lower. These deltas show the RTX 5090 Mobile grouping tightly with desktop and professional cards despite its mobile designation.

Architecture Differences

The two chips share no architectural lineage. The AMD Steam Machine GPU uses the Navi 33 chip built on RDNA 3.0, with the codename Hotpink Bonefish. It belongs to the Console GPU generation for Valve. The process node is 6 nm at TSMC, with 13,300 million transistors on a 204 mm² die. Transistor density reaches 65.2 million per square millimeter. The NVIDIA GeForce RTX 5090 Mobile uses the GB203 chip on Blackwell 2.0, part of the GeForce 50 Mobile generation. Its 5 nm TSMC process packs 45,600 million transistors into 378 mm², for a density of 120.6 million per square millimeter. The NVIDIA part holds more than three times the transistor count on a die that is roughly 85% larger.

Clock behavior differs sharply. The AMD part runs a 1720 MHz base clock, a 2250 MHz game clock, and a 2450 MHz boost clock. The NVIDIA part runs a 990 MHz base and a 1515 MHz boost, with no game clock specified. Despite the lower clocks, the NVIDIA chip reaches higher throughput because of its larger execution resource pool. The AMD part delivers 17.56 TFLOPS FP32 and the same 17.56 TFLOPS FP16 at a 1:1 ratio. The NVIDIA part delivers 31.80 TFLOPS FP32 and 31.80 TFLOPS FP16, also at 1:1.

Shader resources diverge substantially. The AMD GPU uses 1792 shading units, 112 texture mapping units, 64 ROPs, and 28 ray tracing cores, with no tensor cores listed. The NVIDIA GPU uses 10496 shading units, 328 TMUs, 112 ROPs, 82 RT cores, and 328 tensor cores. The NVIDIA part therefore provides roughly 5.9 times the shading units, 2.9 times the TMUs, and 1.75 times the ROPs. Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API feature parity exists despite the internal differences.

Memory architecture is another major split. The AMD GPU uses 8 GB of GDDR6 on a 128 bit bus, producing 288.0 GB/s of bandwidth. The NVIDIA GPU uses 24 GB of GDDR7 on a 256 bit bus, producing 896.0 GB/s. That is three times the capacity and more than three times the bandwidth. The NVIDIA part connects through PCIe 5.0 x16, while the AMD part lists no bus interface. Power figures also differ: the AMD GPU carries a 110 W TDP, the NVIDIA GPU a 95 W TDP. Neither uses external power connectors. The NVIDIA part is an integrated graphics package (IGP) with slot width listed as IGP, while the AMD part has physical dimensions of 156 mm length, 152 mm height, and 162 mm width. The NVIDIA part lists no dimensions. Display outputs differ as well: the AMD GPU provides 1x HDMI 2.1a and 1x DisplayPort 2.1, while the NVIDIA GPU uses portable device dependent outputs.

The Verdict

The data supports a clear split based on measured performance and architectural capacity. The NVIDIA GeForce RTX 5090 Mobile is the only one of the two with recorded benchmark data, and its scores place it in the 84th percentile of all GPUs. It delivers 31.80 TFLOPS FP32, 24 GB of GDDR7 memory, 896.0 GB/s of bandwidth, and 328 tensor cores. These characteristics point toward demanding workloads such as high resolution rendering, ray tracing, and compute acceleration. Its nearest rivals include desktop and professional parts like the AMD Radeon Pro 5500 XT, NVIDIA GeForce RTX 4070 Ti, Intel Arc A730M, and NVIDIA RTX 5880 Ada Generation, all within roughly 2% of its average score. The RTX 5090 Mobile therefore competes above its mobile form factor.

The AMD Steam Machine GPU has no recorded benchmarks, so the database cannot confirm its real world standing. Its specifications describe a 110 W chip with 8 GB of GDDR6, 288.0 GB/s of bandwidth, 17.56 TFLOPS FP32, and 28 RT cores. It targets a console form factor with fixed dimensions and integrated power delivery. The 50th percentile ranking suggests mid-pack placement, but without measurements this remains an estimate from the database classification rather than a tested result. The RTX 5090 Mobile outperforms it in every recorded category, and the architectural gap in shaders, memory, and bandwidth reinforces that ordering.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce RTX 5090 Mobile has an average benchmark score of 45152. The AMD Steam Machine GPU has an average score of zero because no benchmarks are recorded for it.

Q: How much memory does each GPU have?

A: The AMD Steam Machine GPU has 8 GB of GDDR6 memory on a 128 bit bus. The NVIDIA GeForce RTX 5090 Mobile has 24 GB of GDDR7 memory on a 256 bit bus.

Q: Which GPU has more FP32 compute throughput?

A: The NVIDIA GeForce RTX 5090 Mobile delivers 31.80 TFLOPS FP32. The AMD Steam Machine GPU delivers 17.56 TFLOPS FP32.

Q: What are the nearest rivals to the RTX 5090 Mobile in the database?

A: The nearest rivals are the AMD Radeon Pro 5500 XT at 45384 average score (0.5% higher), the NVIDIA GeForce RTX 4070 Ti at 44795 (0.8% lower), the Intel Arc A730M at 45592 (1% higher), and the NVIDIA RTX 5880 Ada Generation at 45972 (1.8% higher).

Q: Do both GPUs support the same graphics APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Q: What is the process node for each GPU?

A: The AMD Steam Machine GPU uses a 6 nm process at TSMC. The NVIDIA GeForce RTX 5090 Mobile uses a 5 nm process at TSMC.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries between these two parts. However, the RTX 5090 Mobile has ten individual benchmark scores that define its measured performance envelope. The largest single score is the Geekbench OpenCL result of 201834, followed by Geekbench Vulkan at 198405. PassMark G3D returns 30034, and PassMark GPU Compute returns 13401. These four scores constitute the high end of its recorded output. The lower end includes PassMark DirectX 9 at 324, DirectX 11 at 269, DirectX 10 at 183, and DirectX 12 at 138. PassMark G2D sits at 1057. 3DMark Steel Nomad DX12 returns 5871.

The AMD Steam Machine GPU has no benchmark data at all, which prevents a direct comparison across any of these tests. Its specifications, however, indicate where it would likely compete. At 17.56 TFLOPS FP32, it delivers roughly 55% of the RTX 5090 Mobile's 31.80 TFLOPS. Its pixel rate of 156.8 GPixel/s trails the NVIDIA part's 169.7 GPixel/s by about 8%. Its texture rate of 274.4 GTexel/s is roughly 45% lower than the NVIDIA part's 496.9 GTexel/s. Memory bandwidth of 288.0 GB/s is less than one third of the NVIDIA part's 896.0 GB/s.

The closest rival comparisons for the RTX 5090 Mobile show a tight cluster. The AMD Radeon Pro 5500 XT scores 45384 on average, only 0.5% above the RTX 5090 Mobile. The Intel Arc A730M scores 45592, 1% above. The NVIDIA RTX 5880 Ada Generation scores 45972, 1.8% above. The NVIDIA GeForce RTX 4070 Ti scores 44795, 0.8% below. These margins indicate that the RTX 5090 Mobile performs within a narrow band of established desktop and workstation parts, despite its 95 W TDP and mobile positioning. The AMD Steam Machine GPU has no comparable rival data in the database, so its placement relative to these parts cannot be quantified.

Specification Differences

The two GPUs differ across nearly every measured specification. The AMD Steam Machine GPU uses the Navi 33 chip on RDNA 3.0 architecture with the codename Hotpink Bonefish, part of the Console GPU generation for Valve. The NVIDIA GeForce RTX 5090 Mobile uses GB203 on Blackwell 2.0 architecture, part of the GeForce 50 Mobile series. The AMD part is fabricated on a 6 nm TSMC process with 13,300 million transistors and a 204 mm² die. The NVIDIA part uses a 5 nm TSMC process with 45,600 million transistors and a 378 mm² die. Transistor density is 65.2 million per mm² for AMD and 120.6 million per mm² for NVIDIA.

Clock speeds differ in base and boost values. The AMD GPU runs at 1720 MHz base and 2450 MHz boost, with a game clock of 2250 MHz and memory clock of 2250 MHz (18 Gbps effective). The NVIDIA GPU runs at 990 MHz base and 1515 MHz boost, with a memory clock of 1750 MHz (28 Gbps effective) and no game clock listed. Memory capacity, type, bus width, and bandwidth all favor NVIDIA: 24 GB GDDR7 on a 256 bit bus at 896.0 GB/s versus 8 GB GDDR6 on a 128 bit bus at 288.0 GB/s.

Execution resources show the largest gap. The AMD GPU has 1792 shading units, 112 TMUs, 64 ROPs, and 28 RT cores, with no tensor cores. The NVIDIA GPU has 10496 shading units, 328 TMUs, 112 ROPs, 82 RT cores, and 328 tensor cores. Pixel rate is 156.8 GPixel/s for AMD and 169.7 GPixel/s for NVIDIA. Texture rate is 274.4 GTexel/s for AMD and 496.9 GTexel/s for NVIDIA. FP32 and FP16 both measure 17.56 TFLOPS for AMD and 31.80 TFLOPS for NVIDIA, with both running at a 1:1 FP16 to FP32 ratio.

Power and physical characteristics also differ. The AMD GPU has a 110 W TDP and physical dimensions of 156 mm length, 152 mm height, and 162 mm width. The NVIDIA GPU has a 95 W TDP, lists no dimensions, and is classified as an IGP with a slot width of IGP. Both use no external power connectors. The AMD GPU offers 1x HDMI 2.1a and 1x DisplayPort 2.1 outputs, while the NVIDIA GPU uses portable device dependent outputs. The NVIDIA part uses a PCIe 5.0 x16 bus interface; the AMD part lists no bus interface. Release dates differ, with the RTX 5090 Mobile released on 2026-06-28 and the AMD Steam Machine GPU on 2025-03-26.