AMD Steam Machine GPU vs Intel Arc Pro B60 Comparison

FAQ

Q: What is the average benchmark score for the Intel Arc Pro B60?

A: The Intel Arc Pro B60 records an average benchmark score of 3182 across the database's test suite. This places it in the 20th percentile of all GPUs tracked.

Q: How does the Intel Arc Pro B60 compare to its nearest rivals?

A: The recorded data shows the Arc Pro B60 sits within 3.5% of several nearby GPUs. It is 0.6% ahead of the NVIDIA Quadro P1000, 0.9% behind the GeForce GT 640, 3.2% behind the GeForce 920M, and 3.5% ahead of the GeForce RTX 5080 SUPER.

Q: What is the AMD Steam Machine GPU's percentile ranking?

A: The AMD Steam Machine GPU holds a 50th percentile position among all GPUs in the database. Its average benchmark score is listed as 0, and no rival comparison data is available for it.

Q: What memory configurations do the two GPUs use?

A: The AMD Steam Machine GPU uses 8 GB of GDDR6 on a 128-bit bus, delivering 288.0 GB/s of bandwidth. The Intel Arc Pro B60 uses 24 GB of GDDR6 on a 192-bit bus, delivering 456.0 GB/s of bandwidth.

Q: Which GPU has the higher FP32 compute throughput?

A: The AMD Steam Machine GPU delivers 17.56 TFLOPS of FP32 compute, while the Intel Arc Pro B60 delivers 12.29 TFLOPS. The AMD part leads in single-precision throughput by a notable margin.

Q: What are the power requirements for each card?

A: The AMD Steam Machine GPU has a TDP of 110 W and requires no external power connectors. The Intel Arc Pro B60 has a TDP of 200 W, uses a single 8-pin connector, and carries a suggested PSU rating of 550 W.

Architecture Differences

The two GPUs represent fundamentally different design philosophies. The AMD Steam Machine GPU uses the Navi 33 chip built on RDNA 3.0 architecture, with the codename Hotpink Bonefish. It belongs to the Console GPU (Valve) generation and is fabricated on TSMC's 6 nm process. The Intel Arc Pro B60 uses the BMG-G21 chip built on Xe2-HPG architecture, belonging to the Battlemage (Pro Series) generation, and is fabricated on TSMC's 5 nm process.

Transistor counts differ significantly. The AMD chip packs 13,300 million transistors on a 204 mm² die, yielding a transistor density of 65.2M per mm². The Intel chip contains 19,600 million transistors on a 272 mm² die, for a density of 72.1M per mm². The Intel die is larger overall, but the density difference indicates a tighter packing of logic on the Xe2-HPG design.

The compute pipelines diverge sharply. AMD's Navi 33 carries 1792 shading units, 112 texture mapping units, 64 ROPs, and 28 ray tracing cores. Intel's BMG-G21 carries 2560 shading units, 160 TMUs, 80 ROPs, and 20 ray tracing cores. Intel leads in raw shader count, texture units, and ROPs, while AMD leads in ray tracing core count. Neither chip includes dedicated tensor cores.

Clock behavior also differs. The AMD part runs a 1720 MHz base clock and 2450 MHz boost, with a 2250 MHz game clock. The Intel part runs a 2000 MHz base clock and 2400 MHz boost, with no game clock specified. The AMD card boosts slightly higher, while the Intel card has a higher base clock.

Memory architecture differences are substantial. AMD uses 8 GB GDDR6 across a 128-bit bus at 2250 MHz (18 Gbps effective), producing 288.0 GB/s bandwidth. Intel uses 24 GB GDDR6 across a 192-bit bus at 2375 MHz (19 Gbps effective), producing 456.0 GB/s bandwidth. The Intel card offers three times the capacity and roughly 58% more bandwidth. The AMD card's FP16 throughput matches its FP32 at 17.56 TFLOPS (1:1 ratio), while the Intel card doubles FP16 to 24.58 TFLOPS (2:1 ratio), which suggests different compute priorities.

Power delivery and physical design differ as well. The AMD card draws 110 W and needs no power connector, fitting into a compact 156 mm by 152 mm by 162 mm envelope. The Intel card draws 200 W, requires a single 8-pin connector and a 550 W PSU, and spans 167 mm by 69 mm by 40 mm as a dual-slot card. The AMD card's squat, cube-like dimensions reflect its console heritage, while the Intel card is a traditional add-in board.

Display outputs also separate the two. The AMD card offers one HDMI 2.1a and one DisplayPort 2.1. The Intel card offers four mini-DisplayPort 2.1 outputs, a configuration aimed at multi-display professional setups.

Head-to-Head Benchmarks

Direct benchmark comparisons are limited because the database contains no head-to-head results between these two specific GPUs. The AMD Steam Machine GPU has no recorded benchmark scores and no nearest rival data. The Intel Arc Pro B60 has eight recorded benchmark results, which provide context for its performance tier.

The Intel Arc Pro B60's strongest result comes from PassMark G3D, where it scores 14580. Its PassMark G2D score is 763. In DirectX 9 workloads it scores 179, in DirectX 11 it scores 122, and in DirectX 12 it scores 76. The compute-oriented PassMark GPU Compute score is 7029. The 3DMark Steel Nomad DX12 test yields 2646.

The Arc Pro B60's average benchmark score of 3182 places it near the GeForce GT 640 (3210, a 0.9% gap) and the Quadro P1000 (3163, a 0.6% gap). It trails the GeForce 920M by 3.2% and leads the RTX 5080 SUPER by 3.5%. These narrow deltas indicate the Intel card occupies a crowded performance band where small margins separate it from both older and newer competition.

Since the AMD card lacks recorded benchmark data, its 50th percentile ranking cannot be cross-referenced against the Arc Pro B60's 20th percentile within the same metric. The percentile gap suggests the AMD card sits higher in the overall distribution, but the absence of direct scores prevents a precise delta calculation.

Specification Differences

The specification sheets reveal clear divergences across nearly every major category:

• Process node: AMD uses 6 nm TSMC; Intel uses 5 nm TSMC.
• Transistors: AMD has 13,300 million; Intel has 19,600 million.
• Die size: AMD measures 204 mm²; Intel measures 272 mm².
• Transistor density: AMD achieves 65.2M per mm²; Intel achieves 72.1M per mm².
• Base clock: AMD runs 1720 MHz; Intel runs 2000 MHz.
• Boost clock: AMD runs 2450 MHz; Intel runs 2400 MHz.
• Memory clock: AMD runs 2250 MHz (18 Gbps effective); Intel runs 2375 MHz (19 Gbps effective).
• Memory size: AMD has 8 GB; Intel has 24 GB.
• Memory bus: AMD uses 128 bit; Intel uses 192 bit.
• Memory bandwidth: AMD delivers 288.0 GB/s; Intel delivers 456.0 GB/s.
• Shading units: AMD has 1792; Intel has 2560.
• TMUs: AMD has 112; Intel has 160.
• ROPs: AMD has 64; Intel has 80.
• Ray tracing cores: AMD has 28; Intel has 20.
• Pixel rate: AMD reaches 156.8 GPixel/s; Intel reaches 192.0 GPixel/s.
• Texture rate: AMD reaches 274.4 GTexel/s; Intel reaches 384.0 GTexel/s.
• FP32: AMD delivers 17.56 TFLOPS; Intel delivers 12.29 TFLOPS.
• FP16: AMD delivers 17.56 TFLOPS (1:1); Intel delivers 24.58 TFLOPS (2:1).
• TDP: AMD draws 110 W; Intel draws 200 W.
• Power connectors: AMD has none; Intel has one 8-pin.
• Suggested PSU: none for AMD; 550 W for Intel.
• Bus interface: not listed for AMD; PCIe 5.0 x8 for Intel.
• Display outputs: AMD has 1x HDMI 2.1a and 1x DisplayPort 2.1; Intel has 4x mini-DisplayPort 2.1.
• Slot width: not listed for AMD; dual-slot for Intel.
• Dimensions: AMD spans 156 mm by 152 mm by 162 mm; Intel spans 167 mm by 69 mm by 40 mm.

Both cards share DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 API support. Both are listed as Active in production status.

Where Each One Wins

The AMD Steam Machine GPU wins decisively in compute throughput per watt. Its FP32 figure of 17.56 TFLOPS at 110 W produces a far more efficient raw compute ratio than the Intel card's 12.29 TFLOPS at 200 W. The AMD card also delivers more ray tracing cores (28 versus 20), which may benefit workloads that scale with RT core count rather than shader throughput. Its compact, power-connector-free design makes it suitable for constrained enclosures where space and power delivery are limited.

The Intel Arc Pro B60 wins in memory capacity and bandwidth. The 24 GB frame buffer at 456.0 GB/s dwarfs the AMD card's 8 GB at 288.0 GB/s. For workloads that exceed 8 GB of working set, the Intel card avoids spillover entirely. Its higher pixel rate (192.0 GPixel/s versus 156.8 GPixel/s) and texture rate (384.0 GTexel/s versus 274.4 GTexel/s) indicate stronger fill-rate performance for resolution-heavy rendering. The FP16 throughput of 24.58 TFLOPS exceeds the AMD card's 17.56 TFLOPS, which may matter for mixed-precision workloads.

The Intel card's four mini-DisplayPort 2.1 outputs support multi-monitor configurations that the AMD card's single HDMI and single DisplayPort cannot match. The PCIe 5.0 x8 interface provides a modern host connection, whereas the AMD card's bus interface is not listed in the database.

The Verdict

The data describes two GPUs with opposite strengths. The AMD Steam Machine GPU prioritizes raw FP32 compute, ray tracing core count, and power efficiency. Its 17.56 TFLOPS at 110 W with no external power connector makes it a low-overhead compute engine. Its 50th percentile ranking suggests it sits near the middle of the database's GPU distribution, though the lack of recorded benchmark scores limits direct verification.

The Intel Arc Pro B60 prioritizes memory capacity, fill rate, and professional connectivity. Its 24 GB frame buffer and 456.0 GB/s bandwidth serve large datasets, while its 192.0 GPixel/s pixel rate and 384.0 GTexel/s texture rate support heavy rasterization. The 20th percentile ranking and average score of 3182 place it near the Quadro P1000 and GeForce GT 640 in the database's overall hierarchy, a modest standing relative to the broader GPU population.

Users needing maximum FP32 compute per watt, a compact physical footprint, and no external power requirement should look to the AMD Steam Machine GPU. Users needing large memory capacity, high bandwidth, superior fill rates, and extensive display output should look to the Intel Arc Pro B60. The launch MSRP for the Intel card is 499 USD. The AMD card's launch MSRP is not recorded in the database. The choice hinges on whether compute efficiency or memory and fill-rate capabilities matter more for the target workload.