AMD Steam Machine GPU vs AMD Xbox Series X 6nm GPU Comparison

Head-to-Head Benchmarks

The database does not currently contain a recorded head-to-head benchmark suite for the AMD Steam Machine GPU and the AMD Xbox Series X 6nm GPU. The wins columns for both parts stand at zero, and the head-to-head benchmark array is empty. As a result, the comparative performance analysis below is derived entirely from the architectural and specification data recorded for each GPU, rather than from direct frame-rate or synthetic score comparisons.

The recorded data does, however, allow a meaningful comparison of theoretical throughput. The Steam Machine GPU delivers 17.56 TFLOPS of FP32 compute, while the Xbox Series X 6nm GPU delivers 12.15 TFLOPS. This places the Steam Machine GPU approximately 45% ahead of the Xbox part in single-precision floating-point throughput. The Steam Machine GPU also achieves a higher pixel rate at 156.8 GPixel/s versus 116.8 GPixel/s, a 34% advantage in raw pixel fill. The texture rate tells the opposite story: the Xbox Series X 6nm GPU reaches 379.6 GTexel/s, which is 38% higher than the Steam Machine GPU’s 274.4 GTexel/s.

The FP16 comparison is inverted. The Steam Machine GPU runs FP16 at a 1:1 ratio with FP32, meaning it sustains the same 17.56 TFLOPS. The Xbox Series X 6nm GPU uses a 2:1 ratio, doubling its FP32 rate to reach 24.29 TFLOPS in FP16. That gives the Xbox part a 38% lead in half-precision compute, a relevant figure for workloads that can exploit packed math.

Memory bandwidth heavily favors the Xbox Series X 6nm GPU. Its 560.0 GB/s bandwidth is nearly double the Steam Machine GPU’s 288.0 GB/s. The Xbox part carries 10 GB of GDDR6 on a 320-bit bus, while the Steam Machine GPU has 8 GB on a 128-bit bus. The memory clock also differs: the Steam Machine GPU runs at 2250 MHz (18 Gbps effective), whereas the Xbox part runs at 1750 MHz (14 Gbps effective). The bus width difference overrides the clock advantage, giving the Xbox part the decisive bandwidth win.

Both GPUs share the same ROP count at 64, so the pixel-rate difference comes purely from clock speed. The Steam Machine GPU’s boost clock of 2450 MHz, with a game clock of 2250 MHz, drives its higher pixel throughput. The Xbox Series X 6nm GPU does not have a recorded base, boost, or game clock, so a direct clock comparison is not possible from the data.

The transistor counts differ as well. The Xbox Series X 6nm GPU contains 15,300 million transistors, while the Steam Machine GPU contains 13,300 million. The Steam Machine GPU’s die size is recorded at 204 mm², giving a transistor density of 65.2 million per mm². The Xbox part’s die size is listed as unknown, so density cannot be calculated for it.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The AMD Steam Machine GPU delivers 17.56 TFLOPS of FP32, which is 45% higher than the AMD Xbox Series X 6nm GPU’s 12.15 TFLOPS.

Q: Which GPU has more memory bandwidth?

A: The AMD Xbox Series X 6nm GPU has 560.0 GB/s of bandwidth, nearly double the AMD Steam Machine GPU’s 288.0 GB/s. The Xbox part uses a 320-bit bus with 10 GB of GDDR6, while the Steam Machine GPU uses a 128-bit bus with 8 GB.

Q: How does the texture rate compare between the two?

A: The AMD Xbox Series X 6nm GPU reaches 379.6 GTexel/s, which is 38% higher than the AMD Steam Machine GPU’s 274.4 GTexel/s.

Q: Do both GPUs support the same DirectX version?

A: Yes, both support DirectX 12 Ultimate (12_2). They also both support OpenGL 4.6. The Vulkan version differs: the Steam Machine GPU supports Vulkan 1.4, while the Xbox Series X 6nm GPU supports Vulkan 1.2.

Q: What is the difference in FP16 throughput?

A: The AMD Xbox Series X 6nm GPU achieves 24.29 TFLOPS in FP16 using a 2:1 ratio, which is 38% higher than the AMD Steam Machine GPU’s 17.56 TFLOPS, which runs FP16 at a 1:1 ratio.

Q: Which GPU has a higher pixel fill rate?

A: The AMD Steam Machine GPU has a pixel rate of 156.8 GPixel/s, which is 34% higher than the AMD Xbox Series X 6nm GPU’s 116.8 GPixel/s. Both parts have 64 ROPs.

Architecture Differences

The two GPUs are built on different RDNA generations. The AMD Steam Machine GPU uses RDNA 3.0 with the Navi 33 chip, codenamed Hotpink Bonefish. The AMD Xbox Series X 6nm GPU uses RDNA 2.0 with the Scarlett 6nm chip. Both are fabricated on a 6 nm process at TSMC, but the architecture revisions differ significantly.

The Steam Machine GPU has 1792 shading units, 112 TMUs, and 64 ROPs. It also includes 28 dedicated ray tracing cores. The Xbox Series X 6nm GPU has 3328 shading units, 208 TMUs, and 64 ROPs, but its ray tracing core count is not recorded in the database. The Steam Machine GPU’s higher FP32 throughput comes from a much higher clock rate: its boost clock is 2450 MHz and its game clock is 2250 MHz. The Xbox part has no recorded clock speeds for base, boost, or game, so the architectural comparison relies on unit counts and throughput figures.

The FP16 execution model differs. The Steam Machine GPU processes FP16 at a 1:1 ratio with FP32, meaning it does not double its rate for half-precision. The Xbox Series X 6nm GPU uses a 2:1 ratio, doubling its FP32 rate to reach 24.29 TFLOPS. This indicates a different shader design between the RDNA 3.0 and RDNA 2.0 architectures, with the older architecture packing more FP16 work per clock.

Vulkan support also differs. The Steam Machine GPU supports Vulkan 1.4, while the Xbox Series X 6nm GPU supports Vulkan 1.2. Both support DirectX 12 Ultimate (12_2) and OpenGL 4.6. The display outputs differ as well: the Steam Machine GPU has one HDMI 2.1a and one DisplayPort 2.1, while the Xbox Series X 6nm GPU has only one HDMI 2.1.

The power envelope is substantially different. The Steam Machine GPU has a TDP of 110 W, while the Xbox Series X 6nm GPU has a TDP of 200 W. The Steam Machine GPU uses no power connectors, whereas the Xbox part’s power connector configuration is not recorded.

Specification Differences

The process node is identical: both are 6 nm TSMC parts. The transistor count differs, with the Xbox Series X 6nm GPU at 15,300 million and the Steam Machine GPU at 13,300 million. The die size is recorded only for the Steam Machine GPU at 204 mm², with the Xbox part listed as unknown.

The memory configuration diverges sharply. The Steam Machine GPU uses 8 GB of GDDR6 on a 128-bit bus with 288.0 GB/s bandwidth. The Xbox Series X 6nm GPU uses 10 GB of GDDR6 on a 320-bit bus with 560.0 GB/s bandwidth. The memory clock is 2250 MHz (18 Gbps effective) for the Steam Machine GPU, versus 1750 MHz (14 Gbps effective) for the Xbox part.

The clock speeds differ in availability. The Steam Machine GPU lists base at 1720 MHz, boost at 2450 MHz, and game at 2250 MHz. The Xbox Series X 6nm GPU lists no base, boost, or game clock. The FP32 throughput favors the Steam Machine GPU at 17.56 TFLOPS versus 12.15 TFLOPS. The FP16 throughput favors the Xbox part at 24.29 TFLOPS versus 17.56 TFLOPS.

The shading unit count is 1792 for the Steam Machine GPU and 3328 for the Xbox Series X 6nm GPU. The TMU count is 112 versus 208. Both have 64 ROPs. The pixel rate is 156.8 GPixel/s for the Steam Machine GPU and 116.8 GPixel/s for the Xbox part. The texture rate is 274.4 GTexel/s versus 379.6 GTexel/s.

The TDP is 110 W for the Steam Machine GPU and 200 W for the Xbox Series X 6nm GPU. The display outputs are one HDMI 2.1a plus one DisplayPort 2.1 for the Steam Machine GPU, versus one HDMI 2.1 for the Xbox part. The Vulkan version is 1.4 for the Steam Machine GPU and 1.2 for the Xbox part.

The physical dimensions differ considerably. The Steam Machine GPU measures 156 mm in length, 152 mm in height, and 162 mm in width. The Xbox Series X 6nm GPU measures 301 mm in length, 151 mm in height, and 151 mm in width. The Xbox part is roughly twice as long.

The release dates differ. The Steam Machine GPU was released on 2026-06-28, while the Xbox Series X 6nm GPU was released on 2024-10-14. The Xbox part has a recorded launch MSRP of 599 USD. The Steam Machine GPU has no recorded launch MSRP.

The production status for both is Active. The Steam Machine GPU’s percentile versus all GPUs is 50, and the Xbox Series X 6nm GPU’s percentile is also 50. Both have an average benchmark score of zero, reflecting the absence of recorded benchmarks.

Where Each One Wins

The AMD Steam Machine GPU wins in raw FP32 compute. Its 17.56 TFLOPS is 45% ahead of the Xbox Series X 6nm GPU’s 12.15 TFLOPS. This advantage extends to pixel fill: 156.8 GPixel/s versus 116.8 GPixel/s, a 34% lead. The Steam Machine GPU also carries a higher boost clock at 2450 MHz and a game clock at 2250 MHz, both of which are absent from the Xbox part’s records. Its 110 W TDP is nearly half the Xbox part’s 200 W, making it the more power-efficient option in the data. The Steam Machine GPU also supports Vulkan 1.4, two versions newer than the Xbox part’s Vulkan 1.2, and it offers a DisplayPort 2.1 output alongside HDMI 2.1a.

The AMD Xbox Series X 6nm GPU wins in memory bandwidth and capacity. Its 560.0 GB/s is 94% higher than the Steam Machine GPU’s 288.0 GB/s, and its 10 GB frame buffer is 2 GB larger. The texture rate also favors the Xbox part at 379.6 GTexel/s, which is 38% higher. The FP16 throughput is another clear win: 24.29 TFLOPS versus 17.56 TFLOPS, a 38% advantage. The Xbox part also has more shading units (3328 versus 1792) and more TMUs (208 versus 112), which supports its higher texture throughput. The Xbox part’s larger transistor count, 15,300 million versus 13,300 million, aligns with its wider memory interface and higher unit counts.

The use-case split follows these strengths. The Steam Machine GPU is better suited for workloads that rely on FP32 shader performance, pixel fill, and lower power draw. The Xbox Series X 6nm GPU is better suited for memory-intensive workloads, high-resolution texture streaming, and FP16 compute tasks.

The Verdict

The data indicates a clear split in strengths. The AMD Steam Machine GPU is the stronger choice for raw single-precision compute and pixel throughput. Its 17.56 TFLOPS FP32 and 156.8 GPixel/s pixel rate outpace the Xbox Series X 6nm GPU by 45% and 34%, respectively. Its 110 W TDP also makes it a far lighter power load. The Steam Machine GPU’s higher clocks, with a 2450 MHz boost, support these throughput advantages.

The AMD Xbox Series X 6nm GPU is the stronger choice for memory-bound scenarios. Its 560.0 GB/s bandwidth is nearly double the Steam Machine GPU’s 288.0 GB/s, and its 10 GB capacity exceeds the Steam Machine GPU’s 8 GB. The texture rate of 379.6 GTexel/s is 38% higher, driven by a larger TMU count. The FP16 throughput of 24.29 TFLOPS is also 38% higher, making it more capable for half-precision workloads.

Users selecting between the two should consider the workload. For general FP32 rendering at lower power, the Steam Machine GPU delivers more compute per watt in the recorded data. For bandwidth-heavy tasks and FP16 compute, the Xbox Series X 6nm GPU provides the wider memory interface and higher half-precision throughput. Both parts sit at the 50th percentile in the database, and neither has recorded benchmark scores, so the verdict rests on the architectural and specification data alone.