Intel Arc Pro B60 Dual vs NVIDIA RTX 5000 Embedded Ada Generation X2 Comparison

Head-to-Head Benchmarks

The database contains no recorded benchmark submissions for either the Intel Arc Pro B60 Dual or the NVIDIA RTX 5000 Embedded Ada Generation X2. Both cards hold a percentile rank of 50 against all GPUs in the database, and their average benchmark scores are zero. Consequently, no head-to-head performance deltas can be derived from recorded measurements, and neither card registers a win in the comparison table.

What the data does reveal is a stark contrast in raw compute specifications, which informs expectations even without direct benchmark results. The RTX 5000 Embedded Ada Generation X2 delivers 32.69 TFLOPS of FP32 throughput, while the Intel Arc Pro B60 Dual delivers 12.29 TFLOPS. That places the NVIDIA part at roughly 2.7 times the FP32 compute of the Intel part, a substantial gap on paper. In FP16, the NVIDIA card holds steady at 32.69 TFLOPS with a 1:1 ratio, whereas the Intel card reaches 24.58 TFLOPS via a 2:1 ratio, meaning the Intel implementation halves its throughput for FP16 work while the NVIDIA implementation does not.

Texture and pixel throughput further separate the two. The RTX 5000 Embedded Ada Generation X2 achieves 510.7 GTexel/s, compared to 384.0 GTexel/s for the Intel Arc Pro B60 Dual. Pixel rates are closer: the NVIDIA card produces 188.2 GPixel/s, while the Intel card produces 192.0 GPixel/s, giving the Intel part a slight edge of about 2% in pixel fill rate. That is a narrow margin, but it indicates the Intel card is not uniformly slower across all rendering stages.

Memory bandwidth tells a different story. The RTX 5000 Embedded Ada Generation X2 uses a 256-bit bus with GDDR6 at 2250 MHz (18 Gbps effective), yielding 576.0 GB/s. The Intel Arc Pro B60 Dual uses a 192-bit bus with GDDR6 at 2375 MHz (19 Gbps effective), yielding 456.0 GB/s. The NVIDIA card holds a 26% bandwidth advantage, which matters for texture-heavy workloads and large frame buffers. However, the Intel card offers 24 GB of memory versus 16 GB on the NVIDIA card, a 50% capacity advantage that benefits workloads exceeding 16 GB, such as large model inference or high-resolution compositing.

Ray tracing resources also differ markedly. The RTX 5000 Embedded Ada Generation X2 includes 76 RT cores, while the Intel Arc Pro B60 Dual includes 20 RT cores. The NVIDIA card also integrates 304 tensor cores, whereas the Intel card reports none in the database. Those architectural resources suggest divergent strengths in ray-traced rendering and AI-accelerated features, though no benchmark scores exist to quantify the real-world impact.

Clock behavior is another distinguishing factor. The Intel Arc Pro B60 Dual runs a base clock of 2000 MHz and a boost clock of 2400 MHz. The NVIDIA RTX 5000 Embedded Ada Generation X2 runs a base clock of 930 MHz and a boost clock of 1680 MHz. Despite lower clocks, the NVIDIA card achieves far higher throughput due to its larger shader count: 9728 shading units versus 2560 on the Intel card. The Intel card compensates with higher clocks and a more compact configuration, but the sheer scale of the NVIDIA silicon dominates in raw arithmetic.

Power consumption is polar opposite. The Intel Arc Pro B60 Dual is rated at 400 W TDP and requires an 800 W suggested PSU with a single 16-pin power connector. The NVIDIA RTX 5000 Embedded Ada Generation X2 is rated at 150 W TDP, has no power connectors listed, and reports no suggested PSU. That 250 W difference positions the Intel card as a desktop-oriented board with substantial cooling and power delivery needs, while the NVIDIA card is an embedded form factor (IGP) designed for systems where slot width and external power cabling are unavailable. The Intel card is dual-slot; the NVIDIA card is integrated into the host platform.

Physical dimensions reinforce the usage split. The Intel Arc Pro B60 Dual measures 300 mm in length, 110 mm in height, and 40 mm in width. The NVIDIA RTX 5000 Embedded Ada Generation X2 lists no dimensions, consistent with an embedded module that does not occupy a standard expansion slot. Display outputs also differ: the Intel card provides 4x mini-DisplayPort 2.1, while the NVIDIA card lists "Portable Device Dependent," meaning displays are determined by the host system rather than the GPU itself.

The Verdict

The data supports a clear division of purpose. The NVIDIA RTX 5000 Embedded Ada Generation X2 holds overwhelming compute advantages: 2.7x FP32 throughput, 2.1x texture rate, 2.2x TMUs, 3.8x RT cores, and 26% more memory bandwidth. It also runs at 150 W TDP with no external power connectors, making it suitable for dense, power-constrained embedded systems where performance per watt is critical. Its 16 GB memory capacity is smaller than the Intel card's 24 GB, but the higher bandwidth and larger shader count give it a strong theoretical edge for most rendering and compute workloads.

The Intel Arc Pro B60 Dual counters with a 50% memory capacity advantage, a slight pixel fill rate lead (192.0 GPixel/s versus 188.2 GPixel/s), and a much higher boost clock (2400 MHz versus 1680 MHz). It also uses PCIe 5.0 x8, whereas the NVIDIA card uses PCIe 4.0 x16, giving the Intel card a newer bus interface. The Intel card is a conventional dual-slot add-in board with four mini-DisplayPort 2.1 outputs, a 400 W TDP, and an 800 W suggested PSU. That makes it a desktop workstation or server GPU for users who need 24 GB of memory and modern display connectivity.

Who should pick which? Strictly from the recorded data, the NVIDIA card is the choice for embedded or mobile applications where power draw, physical footprint, and raw compute are paramount. The Intel card is the choice for desktop builds where memory capacity, display outputs, and a modern PCIe interface matter more than raw FP32 performance. Neither card has benchmark scores in the database, so any performance ranking beyond specifications is not supported by measurements. The percentile rank of 50 for both cards indicates median placement in the overall GPU distribution, but that figure carries no benchmark data behind it.

The absence of recorded benchmarks means the verdict rests entirely on specification analysis. The NVIDIA card's 32.69 TFLOPS FP32 and 510.7 GTexel/s texture rate are decisive on paper. The Intel card's 24 GB memory and 192.0 GPixel/s pixel rate are decisive in capacity and fill-rate terms. Users requiring AI acceleration should note the NVIDIA card's 304 tensor cores, a feature the Intel card does not list. Users requiring 24 GB of GDDR6 on a single card should note the Intel card's capacity advantage.

FAQ

Q: Which card has higher FP32 compute performance?

A: The NVIDIA RTX 5000 Embedded Ada Generation X2 delivers 32.69 TFLOPS FP32, compared to 12.29 TFLOPS on the Intel Arc Pro B60 Dual.

Q: How much memory does each card have?

A: The Intel Arc Pro B60 Dual has 24 GB of GDDR6, while the NVIDIA RTX 5000 Embedded Ada Generation X2 has 16 GB of GDDR6.

Q: What is the memory bandwidth difference?

A: The NVIDIA card provides 576.0 GB/s, while the Intel card provides 456.0 GB/s, a 26% advantage for the NVIDIA part.

Q: Which card has more ray tracing cores?

A: The NVIDIA RTX 5000 Embedded Ada Generation X2 has 76 RT cores, while the Intel Arc Pro B60 Dual has 20 RT cores.

Q: What are the power requirements?

A: The Intel card has a 400 W TDP, uses a 1x 16-pin power connector, and suggests an 800 W PSU. The NVIDIA card has a 150 W TDP and lists no power connectors or PSU suggestion.

Q: Which card uses a newer PCIe interface?

A: The Intel Arc Pro B60 Dual uses PCIe 5.0 x8, while the NVIDIA RTX 5000 Embedded Ada Generation X2 uses PCIe 4.0 x16.

Specification Differences

| Field | Intel Arc Pro B60 Dual | NVIDIA RTX 5000 Embedded Ada Generation X2 |

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

| Shading units | 2560 | 9728 |

| TMUs | 160 | 304 |

| ROPs | 80 | 112 |

| RT cores | 20 | 76 |

| Tensor cores | None | 304 |

| FP32 | 12.29 TFLOPS | 32.69 TFLOPS |

| FP16 | 24.58 TFLOPS (2:1) | 32.69 TFLOPS (1:1) |

| Pixel rate | 192.0 GPixel/s | 188.2 GPixel/s |

| Texture rate | 384.0 GTexel/s | 510.7 GTexel/s |

| Memory size | 24 GB | 16 GB |

| Memory bus width | 192 bit | 256 bit |

| Memory bandwidth | 456.0 GB/s | 576.0 GB/s |

| Base clock | 2000 MHz | 930 MHz |

| Boost clock | 2400 MHz | 1680 MHz |

| TDP | 400 W | 150 W |

| Slot width | Dual-slot | IGP |

| Power connectors | 1x 16-pin | None |

| Suggested PSU | 800 W | None |

| Bus interface | PCIe 5.0 x8 | PCIe 4.0 x16 |

| Display outputs | 4x mini-DisplayPort 2.1 | Portable Device Dependent |

| Dimensions | 300 mm x 110 mm x 40 mm | Not listed |

| Launch MSRP | 1,199 USD | None |

Architecture Differences

The Intel Arc Pro B60 Dual uses the BMG-G21 chip built on the Xe2-HPG architecture, part of the Battlemage (Pro Series) generation. It is fabricated on a 5 nm process at TSMC, with 19,600 million transistors on a 272 mm² die, yielding a transistor density of 72.1M per mm². The architecture supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Memory is GDDR6 on a 192-bit bus, clocked at 2375 MHz (19 Gbps effective). The card is a dual-slot, 400 W design with an 800 W suggested PSU.

The NVIDIA RTX 5000 Embedded Ada Generation X2 uses the AD103 chip built on the Ada Lovelace architecture, part of the Ada-MW generation. It is also fabricated on a 5 nm process at TSMC, but carries 45,900 million transistors on a 379 mm² die, yielding a transistor density of 121.1M per mm². That is 2.3x the transistor count and 1.4x the die size of the Intel chip, with a 68% higher transistor density. The architecture supports the same API set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Memory is GDDR6 on a 256-bit bus, clocked at 2250 MHz (18 Gbps effective).

The NVIDIA card integrates 304 tensor cores, a feature absent from the Intel card's listed specifications. The RT core counts differ substantially: 76 on NVIDIA versus 20 on Intel. The NVIDIA card is an IGP (integrated graphics processor) form factor with no power connectors, a 150 W TDP, and no suggested PSU, indicating it is designed for embedded systems where the host provides power and cooling. The Intel card is a standard dual-slot expansion board with a 16-pin connector and a 400 W TDP, indicating a desktop or rack workstation orientation.

The Intel card's memory clock is higher (2375 MHz versus 2250 MHz), but the NVIDIA card's wider 256-bit bus gives it higher total bandwidth. The Intel card's PCIe 5.0 x8 interface is a newer generation than NVIDIA's PCIe 4.0 x16, though the NVIDIA interface offers more lanes. The release dates reflect different market timing: the NVIDIA card entered production status in March 2023, while the Intel card became active in September 2025. The NVIDIA card's predecessor is Ampere-MW and its successor is Blackwell-MW, while the Intel card lists no predecessor or successor in the database.