Intel Arc Pro B60 vs NVIDIA N1 16SM Comparison

The Verdict

The Intel Arc Pro B60 and NVIDIA N1 16SM target fundamentally different segments, and the recorded data confirms they should not be cross-shopped for the same workload. The Arc Pro B60 is a discrete workstation GPU with a full benchmark profile, while the N1 16SM is an integrated graphics processor (IGP) with no recorded benchmark scores. The Arc Pro B60 delivers 12.29 TFLOPS FP32 compute, 456.0 GB/s memory bandwidth, and 24 GB of GDDR6, making it suitable for rendering and compute tasks. The N1 16SM offers 9.609 TFLOPS FP32, 273.2 GB/s bandwidth, and 128 GB of LPDDR5X, but its lack of DirectX, OpenGL, and Vulkan API support means it cannot run conventional graphics workloads. The data shows the Arc Pro B60 is the only option for software that relies on standard graphics APIs. The N1 16SM, with its IGP form factor and no power connectors, serves as a system-on-chip solution for devices where discrete expansion is not possible. The Arc Pro B60 has a launch MSRP of 499 USD, but the N1 16SM has no listed launch MSRP.

Architecture Differences

The Intel Arc Pro B60 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 NVIDIA N1 16SM uses the GB20B chip built on the Blackwell 2.0 architecture, part of the Blackwell IGP (N1x) generation. It is also fabricated on a 5 nm process at TSMC, but its transistor count is unknown, and it uses a larger 382 mm² die with no recorded transistor density.

The Arc Pro B60 features 2560 shading units, 160 texture mapping units, 80 raster output units, and 20 ray tracing cores. The N1 16SM has 2048 shading units, 128 TMUs, 24 ROPs, and 16 ray tracing cores, but it adds 64 tensor cores, a feature the Arc Pro B60 lacks. The Arc Pro B60 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, while the N1 16SM lists DirectX, OpenGL, and Vulkan as N/A. The Arc Pro B60 uses a 192-bit memory bus with GDDR6, while the N1 16SM uses a 256-bit bus with LPDDR5X. The Arc Pro B60 is a dual-slot card requiring a 1x 8-pin power connector and a 550 W suggested PSU, whereas the N1 16SM is an IGP with no power connectors and no suggested PSU.

FAQ

Q: Which GPU has higher FP32 compute performance?

A: The Intel Arc Pro B60 delivers 12.29 TFLOPS FP32, which is 27.9% higher than the NVIDIA N1 16SM's 9.609 TFLOPS FP32.

Q: Which GPU has more memory bandwidth?

A: The Intel Arc Pro B60 has 456.0 GB/s bandwidth, which is 66.9% higher than the NVIDIA N1 16SM's 273.2 GB/s bandwidth.

Q: Which GPU supports standard graphics APIs?

A: Only the Intel Arc Pro B60 supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The NVIDIA N1 16SM lists all three APIs as N/A.

Q: Which GPU has more memory capacity?

A: The NVIDIA N1 16SM has 128 GB of LPDDR5X, which is 5.3 times the 24 GB of GDDR6 found on the Intel Arc Pro B60.

Q: Which GPU has a higher boost clock?

A: The Intel Arc Pro B60 boosts to 2400 MHz, which is 2.3% higher than the NVIDIA N1 16SM's 2346 MHz boost clock.

Q: Which GPU has more texture mapping units?

A: The Intel Arc Pro B60 has 160 TMUs, which is 25% more than the NVIDIA N1 16SM's 128 TMUs.

Specification Differences

The two GPUs differ across nearly every recorded specification. The Intel Arc Pro B60 uses a 5 nm process with 19,600 million transistors on a 272 mm² die, while the NVIDIA N1 16SM uses a 5 nm process with unknown transistors on a 382 mm² die. The Arc Pro B60 has a base clock of 2000 MHz and boost of 2400 MHz, while the N1 16SM has a base clock of 741 MHz and boost of 2346 MHz. Memory differs substantially: the Arc Pro B60 has 24 GB GDDR6 on a 192-bit bus with 456.0 GB/s bandwidth, while the N1 16SM has 128 GB LPDDR5X on a 256-bit bus with 273.2 GB/s bandwidth. Memory clocks are 2375 MHz (19 Gbps effective) for the Arc Pro B60 versus 1067 MHz (8.5 Gbps effective) for the N1 16SM.

Compute resources differ: the Arc Pro B60 has 2560 shading units, 160 TMUs, 80 ROPs, and 20 RT cores, while the N1 16SM has 2048 shading units, 128 TMUs, 24 ROPs, 16 RT cores, and 64 tensor cores. Pixel rate is 192.0 GPixel/s for the Arc Pro B60 versus 56.30 GPixel/s for the N1 16SM. Texture rate is 384.0 GTexel/s versus 300.3 GTexel/s. FP16 compute is 24.58 TFLOPS (2:1) for the Arc Pro B60 versus 9.609 TFLOPS (1:1) for the N1 16SM. The Arc Pro B60 has a 200 W TDP, while the N1 16SM's TDP is unknown. Form factors differ: the Arc Pro B60 is dual-slot with a 1x 8-pin connector and 550 W suggested PSU, while the N1 16SM is an IGP with no connectors. Bus interface is PCIe 5.0 x8 for the Arc Pro B60 versus PCIe 5.0 x16 for the N1 16SM. Display outputs are 4x mini-DisplayPort 2.1 versus 1x HDMI. The Arc Pro B60 measures 167 mm x 69 mm x 40 mm, while the N1 16SM has no recorded dimensions.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries between the Intel Arc Pro B60 and NVIDIA N1 16SM, and the N1 16SM has an empty benchmark array. The Arc Pro B60, however, has eight recorded benchmark scores. In 3DMark Steel Nomad DX12, it scores 2646. In PassMark tests, it scores 61 in DirectX 10, 122 in DirectX 11, 76 in DirectX 12, 179 in DirectX 9, 763 in G2D, 14580 in G3D, and 7029 in GPU compute. Its average benchmark score is 3182, placing it at the 20th percentile of all GPUs. The N1 16SM has an average benchmark score of 0 and sits at the 50th percentile, but this percentile is based on no recorded performance data.

The Arc Pro B60's nearest rivals in the database provide context for its performance tier. The NVIDIA Quadro P1000 averages 3163, which is 0.6% lower than the Arc Pro B60's 3182. The NVIDIA GeForce GT 640 averages 3210, which is 0.9% higher. The NVIDIA GeForce 920M averages 3287, which is 3.2% higher. The NVIDIA GeForce RTX 5080 SUPER averages 3075, which is 3.5% lower. These deltas show the Arc Pro B60 sits in a narrow performance band among these rivals, with all four within a 3.5% range of its average score. The data indicates the Arc Pro B60's compute-heavy workload results (7029 in GPU compute) contrast with its rasterization scores, suggesting a specialization in compute over traditional graphics.

Where Each One Wins

The Intel Arc Pro B60 wins in every measurable performance category that the database records. Its FP32 compute of 12.29 TFLOPS exceeds the N1 16SM's 9.609 TFLOPS by 27.9%. Its texture rate of 384.0 GTexel/s beats 300.3 GTexel/s by 27.9%. Its pixel rate of 192.0 GPixel/s is 3.4 times the N1 16SM's 56.30 GPixel/s. Its memory bandwidth of 456.0 GB/s exceeds 273.2 GB/s by 66.9%. Its boost clock of 2400 MHz is marginally higher than 2346 MHz. Its shading unit count of 2560 exceeds 2048 by 25%, and its ROP count of 80 exceeds 24 by a factor of 3.3.

The NVIDIA N1 16SM wins in memory capacity, offering 128 GB versus 24 GB, a 5.3 times advantage. It also has 64 tensor cores, which the Arc Pro B60 lacks entirely. The N1 16SM uses a PCIe 5.0 x16 interface versus the Arc Pro B60's PCIe 5.0 x8, providing double the bus lanes. Its die size of 382 mm² is 40.4% larger than the Arc Pro B60's 272 mm², though this does not translate into performance advantages in the recorded data.

For use-case analysis, the Arc Pro B60 is the clear choice for any workload requiring standard graphics APIs, given the N1 16SM lists DirectX, OpenGL, and Vulkan as N/A. The Arc Pro B60's higher FP32 and FP16 throughput, along with its 20 RT cores, positions it for rendering, compute, and ray-traced workloads. The N1 16SM's 128 GB memory capacity and 64 tensor cores suggest a role in large-model inference or data processing, but its lack of API support and absence of benchmark data prevent quantitative verification. The N1 16SM's IGP form factor and lack of power connectors make it suitable only for integrated systems where the Arc Pro B60's dual-slot, 200 W discrete card cannot fit. The recorded data supports the Arc Pro B60 for all measured graphics and compute benchmarks, while the N1 16SM's advantages remain limited to memory capacity, tensor core presence, and bus width.