AMD Steam Machine GPU vs Intel Arc Pro B60 Dual Comparison

The Verdict

The AMD Steam Machine GPU and Intel Arc Pro B60 Dual serve fundamentally different roles, despite both being active products in the database. The Steam Machine GPU is a console-oriented part built around efficiency and compactness, while the Arc Pro B60 Dual is a professional workstation card that prioritizes memory capacity and sustained throughput. The measured data shows both sit at the 50th percentile among all GPUs, with no head-to-head benchmarks recorded, meaning buyers must weigh their specific needs against the architectural and specification differences.

The Steam Machine GPU suits users who need a low-power, space-constrained solution. Its 110 W TDP, lack of power connectors, and compact dimensions (156 mm length, 152 mm height, 162 mm width) make it ideal for small-form-factor builds or embedded console-style systems. It delivers a higher FP32 throughput of 17.56 TFLOPS, which indicates strong raw shader performance for its class. The Arc Pro B60 Dual, by contrast, demands a 400 W TDP, an 800 W suggested PSU, and a 16-pin connector, plus a 300 mm length. It targets professionals who require 24 GB of VRAM and a 456.0 GB/s memory bandwidth, which the Steam Machine GPU cannot approach with its 8 GB and 288.0 GB/s.

The Arc Pro B60 Dual also includes 4x mini-DisplayPort 2.1 outputs, suggesting multi-display professional workflows. Its launch MSRP is 1,199 USD. The Steam Machine GPU has no launch MSRP recorded. For gaming-oriented or low-power applications, the Steam Machine GPU's higher FP32 rate and lower power draw make it a practical choice. For content creation, large dataset handling, or any task needing extensive VRAM, the Arc Pro B60 Dual is the only option with the required memory resources.

Architecture Differences

The two GPUs use different architectures from different generations. The AMD Steam Machine GPU is built on RDNA 3.0, with the chip codename Hotpink Bonefish, and belongs to the Console GPU (Valve) generation. It uses a 6 nm process at TSMC, housing 13,300 million transistors on a 204 mm² die, giving a transistor density of 65.2M per mm². The Intel Arc Pro B60 Dual uses Xe2-HPG architecture, specifically the Battlemage (Pro Series) generation, with the BMG-G21 chip. It is fabricated on a 5 nm process at TSMC, with 19,600 million transistors across a 272 mm² die, resulting in a higher density of 72.1M per mm².

The compute layouts differ significantly. The Steam Machine GPU has 1792 shading units, 112 texture mapping units, and 64 ROPs, alongside 28 ray-tracing cores. The Arc Pro B60 Dual provides 2560 shading units, 160 TMUs, and 80 ROPs, but only 20 ray-tracing cores. This means Intel allocates more resources to standard rasterization throughput per clock, while AMD dedicates more hardware to ray tracing relative to its shading unit count.

Clock speeds also differ. The Steam Machine GPU has a base clock of 1720 MHz, a boost of 2450 MHz, and a game clock of 2250 MHz. The Arc Pro B60 Dual runs at a 2000 MHz base and 2400 MHz boost, with no game clock specified. Memory clocks are close: 2250 MHz (18 Gbps effective) for AMD versus 2375 MHz (19 Gbps effective) for Intel. The FP16 capabilities diverge: the Steam Machine GPU delivers 17.56 TFLOPS at a 1:1 ratio with FP32, while the Arc Pro B60 Dual achieves 24.58 TFLOPS at a 2:1 ratio, indicating Intel's architecture processes half-precision workloads at twice the rate of single-precision.

Power characteristics reflect their intended environments. The Steam Machine GPU draws 110 W and requires no external power connectors, relying entirely on slot power. The Arc Pro B60 Dual draws 400 W, needs a single 16-pin connector, and specifies an 800 W suggested PSU. The Steam Machine GPU also omits a bus interface specification, while the Arc Pro B60 Dual uses PCIe 5.0 x8. Display outputs differ: the Steam Machine GPU offers 1x HDMI 2.1a and 1x DisplayPort 2.1, whereas the Arc Pro B60 Dual provides 4x mini-DisplayPort 2.1.

FAQ

Q: Which GPU has more VRAM?

A: The Intel Arc Pro B60 Dual has 24 GB of GDDR6 memory, while the AMD Steam Machine GPU has 8 GB of GDDR6.

Q: How do their power requirements compare?

A: The AMD Steam Machine GPU has a 110 W TDP and needs no power connectors. The Intel Arc Pro B60 Dual has a 400 W TDP, requires a 16-pin connector, and suggests an 800 W power supply.

Q: Which card has higher single-precision floating-point performance?

A: The AMD Steam Machine GPU leads in FP32 with 17.56 TFLOPS, compared to the Intel Arc Pro B60 Dual's 12.29 TFLOPS.

Q: Are the memory bandwidths different?

A: Yes. The Intel Arc Pro B60 Dual provides 456.0 GB/s over a 192-bit bus, while the AMD Steam Machine GPU offers 288.0 GB/s over a 128-bit bus.

Q: Which GPU supports more display outputs?

A: The Intel Arc Pro B60 Dual has 4x mini-DisplayPort 2.1 outputs. The AMD Steam Machine GPU has 1x HDMI 2.1a and 1x DisplayPort 2.1.

Q: What are their physical sizes?

A: The AMD Steam Machine GPU measures 156 mm in length, 152 mm in height, and 162 mm in width. The Intel Arc Pro B60 Dual is 300 mm long, 110 mm high, and 40 mm wide, and it is a dual-slot card.

Specification Differences

The recorded data shows the two GPUs differ across nearly every measurable specification. The process node favors Intel: 5 nm versus 6 nm for AMD, though both use TSMC. Intel's die is larger at 272 mm² versus 204 mm², and it packs more transistors at 19,600 million versus 13,300 million. Transistor density is higher on Intel at 72.1M per mm² versus 65.2M per mm².

Memory capacity and bandwidth are the starkest differences. The Steam Machine GPU provides 8 GB of GDDR6 on a 128-bit bus, yielding 288.0 GB/s. The Arc Pro B60 Dual provides 24 GB of GDDR6 on a 192-bit bus, yielding 456.0 GB/s. This threefold capacity advantage and 58% bandwidth advantage position Intel for memory-intensive tasks.

Compute resources are split. The Steam Machine GPU has fewer shading units (1792 versus 2560), TMUs (112 versus 160), and ROPs (64 versus 80), but more ray-tracing cores (28 versus 20). The pixel rate favors Intel at 192.0 GPixel/s versus 156.8 GPixel/s, and the texture rate favors Intel at 384.0 GTexel/s versus 274.4 GTexel/s. FP32 favors AMD at 17.56 TFLOPS versus 12.29 TFLOPS, while FP16 favors Intel at 24.58 TFLOPS versus 17.56 TFLOPS.

Clocks are comparable but not identical. AMD's base clock is 1720 MHz versus Intel's 2000 MHz, while boost clocks are 2450 MHz versus 2400 MHz. AMD specifies a game clock of 2250 MHz; Intel does not record one. Memory clock is slightly higher on Intel at 2375 MHz versus 2250 MHz. The API support is identical: both feature DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Power and physical requirements diverge sharply. The Steam Machine GPU has a 110 W TDP, no power connectors, and no suggested PSU. The Arc Pro B60 Dual has a 400 W TDP, a 16-pin connector, and an 800 W suggested PSU. The Steam Machine GPU is a compact 156 mm by 152 mm by 162 mm, while the Arc Pro B60 Dual is a dual-slot 300 mm by 110 mm by 40 mm. The bus interface differs too: Intel uses PCIe 5.0 x8, while AMD does not list a bus interface. Release dates also differ: the Steam Machine GPU has a 2026-06-28 release date, and the Arc Pro B60 Dual has a 2025-09-04 release date.

Head-to-Head Benchmarks

No head-to-head benchmark results exist between these two GPUs in the database. Both have an average benchmark score of 0 and zero wins recorded. The percentile ranking is identical at 50 for each, indicating they sit at the median of all GPUs tracked. Without direct comparative measurements, the analysis must rely on the specification-level data to project performance characteristics.

The most significant performance indicator differences come from the compute and memory specifications. The Steam Machine GPU's FP32 output of 17.56 TFLOPS exceeds the Arc Pro B60 Dual's 12.29 TFLOPS by roughly 43%, suggesting AMD holds a clear advantage in workloads that scale with single-precision shader throughput. The texture rate, however, favors Intel at 384.0 GTexel/s versus 274.4 GTexel/s, a 40% lead that indicates better texel-fill capacity for texture-heavy rendering. The pixel rate also favors Intel at 192.0 GPixel/s versus 156.8 GPixel/s, a 22% advantage for rasterization-bound scenarios.

Memory bandwidth differences are substantial. The Arc Pro B60 Dual's 456.0 GB/s is 58% higher than the Steam Machine GPU's 288.0 GB/s. Combined with 24 GB of VRAM versus 8 GB, Intel's card can sustain higher data throughput and hold far larger working sets. This matters for tasks like rendering large scenes, processing high-resolution textures, or running AI inference with big models. The FP16 performance of 24.58 TFLOPS on Intel versus 17.56 TFLOPS on AMD also signals that half-precision compute workloads will run faster on the Arc Pro B60 Dual, assuming software can use the 2:1 FP16 mode.

Ray-tracing resources favor AMD, with 28 ray-tracing cores versus Intel's 20. Clock speeds are close enough that this core count difference likely translates to better ray-tracing throughput on the Steam Machine GPU, though the absence of benchmark data prevents confirmation. The power envelope compounds this: the Steam Machine GPU achieves its performance at 110 W, while the Arc Pro B60 Dual needs 400 W, meaning AMD delivers its FP32 lead at less than a third of the power draw.

Where Each One Wins

The AMD Steam Machine GPU wins in scenarios that prioritize raw FP32 throughput and efficiency. Its 17.56 TFLOPS of single-precision compute exceeds Intel's 12.29 TFLOPS, making it the stronger choice for gaming workloads, general 3D rendering that relies on shader math, and any application where FP32 performance is the bottleneck. The 110 W TDP and lack of power connectors mean it can operate in systems without dedicated power cabling, which suits compact consoles, small-form-factor PCs, or low-power builds. Its 28 ray-tracing cores also give it an edge in ray-traced graphics tasks, assuming the software uses them effectively. The smaller physical footprint (156 mm by 152 mm by 162 mm) allows installation in tight chassis where the 300 mm Arc Pro B60 Dual cannot fit.

The Intel Arc Pro B60 Dual wins in memory-bound and professional workloads. Its 24 GB VRAM is three times the Steam Machine GPU's 8 GB, enabling work with large datasets, high-resolution textures, complex 3D scenes, or multi-model AI inference that would exceed AMD's memory capacity. The 456.0 GB/s bandwidth is 58% higher, so any task that streams data heavily will benefit. The 384.0 GTexel/s texture rate and 192.0 GPixel/s pixel rate beat AMD's 274.4 GTexel/s and 156.8 GPixel/s, making Intel the better option for fill-rate-heavy rendering passes. The FP16 performance of 24.58 TFLOPS at a 2:1 ratio doubles AMD's 17.56 TFLOPS, giving Intel a clear win for half-precision compute, common in machine learning training and inference. The 4x mini-DisplayPort 2.1 outputs support multi-monitor professional setups, while the single HDMI and single DisplayPort on the Steam Machine GPU limit such configurations.

The PCIe 5.0 x8 interface on the Arc Pro B60 Dual provides a modern connection for data transfer, though the Steam Machine GPU does not list an interface specification. The Arc Pro B60 Dual also has a higher transistor count (19,600 million versus 13,300 million) and a larger die (272 mm² versus 204 mm²), which suggests more total hardware resources for parallel workloads, even if the FP32 rate is lower. The 2000 MHz base clock on Intel versus 1720 MHz on AMD means Intel runs faster at idle-to-light loads, but the boost clocks are nearly identical at 2400 MHz versus 2450 MHz.

The production status is active for both, and neither has a listed predecessor or successor. The Arc Pro B60 Dual has a launch MSRP of 1,199 USD, while the Steam Machine GPU has no recorded price. Release dates show Intel shipping earlier on 2025-09-04 versus AMD on 2026-06-28. For users who need maximum shader throughput in a low-power, small package, the Steam Machine GPU is the data-supported choice. For users who need vast memory, high bandwidth, and professional display outputs, the Arc Pro B60 Dual delivers those capabilities with the tradeoff of high power consumption and a larger physical footprint.