Intel Arc Pro B390 vs NVIDIA GeForce RTX 4060 Ti AD104 Comparison

FAQ

Q: What are the two products compared in this analysis?

A: The Intel Arc Pro B390 is an integrated graphics processor (IGP) based on the Panther Lake chip with Xe3-LPG architecture, built on a 3 nm process at Intel. The NVIDIA GeForce RTX 4060 Ti AD104 is a dual-slot discrete graphics card from the GeForce 40-series, using Ada Lovelace architecture on a 5 nm process at TSMC.

Q: How do the memory configurations differ?

A: The Intel Arc Pro B390 uses system-shared memory with system-dependent bandwidth, meaning it has no dedicated VRAM. The NVIDIA GeForce RTX 4060 Ti AD104 has 8 GB of GDDR6 memory on a 128-bit bus with 288.0 GB/s bandwidth.

Q: What is the difference in thermal design power?

A: The Intel Arc Pro B390 has a TDP of 80 W and uses no power connectors, being an IGP. The NVIDIA GeForce RTX 4060 Ti AD104 has a TDP of 160 W, requires a single 16-pin power connector, and has a suggested PSU rating of 450 W.

Q: Which product has higher raw compute throughput?

A: The NVIDIA GeForce RTX 4060 Ti AD104 delivers 22.06 TFLOPS of FP32 performance, which is approximately 2.9 times the 7.680 TFLOPS of the Intel Arc Pro B390.

Q: What are the release dates and production statuses?

A: The Intel Arc Pro B390 was released on 2026-01-26 and is currently marked as Active in production. The NVIDIA GeForce RTX 4060 Ti AD104 was released on 2024-03-31 and is marked as End-of-life.

Q: Do both products support the same graphics APIs?

A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The primary API differences lie elsewhere in their hardware implementations, not in the API feature levels.

Architecture Differences

The two processors represent fundamentally different design philosophies. The Intel Arc Pro B390 is an integrated GPU built into the Panther Lake chip, using the Xe3-LPG architecture. The process node is 3 nm, fabricated by Intel. This architecture focuses on efficiency and integration, with the GPU sharing system memory rather than having dedicated VRAM. The NVIDIA GeForce RTX 4060 Ti AD104 is a discrete add-in board using the AD104 chip on the Ada Lovelace architecture. It is fabricated on a 5 nm process by TSMC, with a transistor count of 35,800 million on a 294 mm² die, giving a transistor density of 121.8M per mm².

The core configurations diverge sharply. The Intel Arc Pro B390 contains 1,536 shading units, 48 texture mapping units, and 24 raster output pipelines. It has 12 ray tracing cores and no dedicated tensor cores. The NVIDIA GeForce RTX 4060 Ti AD104 contains 4,352 shading units, 136 TMUs, and 48 ROPs. It has 34 ray tracing cores and 136 tensor cores. The NVIDIA part has nearly three times the shading units, nearly three times the TMUs, and double the ROPs. The tensor core count on the NVIDIA part is particularly significant for AI-accelerated workloads, a feature entirely absent from the Intel IGP.

Clock behavior also differs. The Intel Arc Pro B390 has a base clock of 300 MHz and a boost clock of 2500 MHz, with memory clocked as system shared. The NVIDIA GeForce RTX 4060 Ti AD104 has a base clock of 2310 MHz and a boost clock of 2535 MHz, with memory running at 2250 MHz (18 Gbps effective). The NVIDIA part also has a much narrower boost range, while the Intel part has an extremely low base clock, indicating heavy power management on the integrated solution.

Memory architecture is a fundamental differentiator. The Intel Arc Pro B390 uses system-shared memory with a system-dependent bus width and bandwidth. The NVIDIA GeForce RTX 4060 Ti AD104 has 8 GB of dedicated GDDR6 memory on a 128-bit bus, providing 288.0 GB/s of bandwidth. This dedicated memory bandwidth is critical for sustained gaming and compute workloads, as it does not compete with CPU memory access.

The physical and power profiles are also distinct. The Intel Arc Pro B390 is an IGP with no slot width, no power connectors, and no suggested PSU. The NVIDIA GeForce RTX 4060 Ti AD104 is a dual-slot card measuring 240 mm in length, 111 mm in height, and 40 mm in width, requiring a 16-pin connector and a 450 W suggested PSU. The bus interface differs as well: the Intel part uses IGP, while the NVIDIA part uses PCIe 4.0 x8.

Head-to-Head Benchmarks

The recorded data shows no direct head-to-head benchmark entries, and both products have an average benchmark score of 0 with no nearest rivals listed. However, the specification-level comparison provides clear performance indicators. The NVIDIA GeForce RTX 4060 Ti AD104 delivers 22.06 TFLOPS of FP32 compute, which is 2.87 times the 7.680 TFLOPS of the Intel Arc Pro B390. In FP16, the NVIDIA part delivers 22.06 TFLOPS at a 1:1 ratio, while the Intel part delivers 15.36 TFLOPS at a 2:1 ratio. This means the NVIDIA part outperforms in both precision formats, but the Intel part shows a higher FP16-to-FP32 ratio, indicating that it can double its throughput when using reduced precision.

Pixel throughput favors the NVIDIA part decisively. The NVIDIA GeForce RTX 4060 Ti AD104 achieves 121.7 GPixel/s compared to 60.00 GPixel/s for the Intel Arc Pro B390, a 2.03 times advantage. Texture rate shows a similar pattern: the NVIDIA part delivers 344.8 GTexel/s versus 120.0 GTexel/s for the Intel part, a 2.87 times advantage. These ratios align closely with the shading unit and TMU counts, indicating that the architectural scaling is consistent across these metrics.

The ray tracing capability is also heavily skewed. The NVIDIA GeForce RTX 4060 Ti AD104 has 34 ray tracing cores versus 12 on the Intel Arc Pro B390, a 2.83 times difference. Combined with the presence of 136 tensor cores on the NVIDIA part versus none on the Intel part, the NVIDIA card is positioned for substantially heavier ray-traced and AI-accelerated workloads. The Intel part, lacking tensor cores entirely, cannot offload AI inference tasks to dedicated hardware.

Memory bandwidth is another major separator. The NVIDIA GeForce RTX 4060 Ti AD104 provides 288.0 GB/s of dedicated bandwidth, while the Intel Arc Pro B390's bandwidth is system-dependent, meaning it varies with the host platform's memory configuration. In typical system-shared implementations, dedicated bandwidth is far lower than a discrete card's dedicated VRAM bandwidth. This affects texture streaming, high-resolution rendering, and large dataset processing.

The clock speeds show a different trade-off. The NVIDIA part's base clock of 2310 MHz is 7.7 times the Intel part's base clock of 300 MHz, though the boost clocks are closer: 2535 MHz versus 2500 MHz. The Intel part's low base clock suggests aggressive power gating at idle, while the NVIDIA part maintains a higher floor. The NVIDIA part's boost clock is only 1.4% higher than the Intel part's boost clock, indicating that the Intel IGP can reach competitive peak frequencies when power is available.

Specification Differences

The following fields differ between the two products. The Intel Arc Pro B390 uses the Panther Lake chip with Xe3-LPG architecture, while the NVIDIA GeForce RTX 4060 Ti AD104 uses the AD104 chip with Ada Lovelace architecture. The process nodes are 3 nm (Intel) versus 5 nm (TSMC). The NVIDIA part has 35,800 million transistors on a 294 mm² die with a 121.8M per mm² density; the Intel part's transistor count and die size are unknown.

Clock specifications differ: the Intel part has a 300 MHz base and 2500 MHz boost, while the NVIDIA part has a 2310 MHz base and 2535 MHz boost. Memory configurations are entirely different: the Intel part uses system-shared memory with system-dependent bandwidth, while the NVIDIA part has 8 GB GDDR6 on a 128-bit bus with 288.0 GB/s bandwidth. Shading units are 1,536 versus 4,352; TMUs are 48 versus 136; ROPs are 24 versus 48; ray tracing cores are 12 versus 34; tensor cores are absent versus 136.

Pixel rate is 60.00 GPixel/s versus 121.7 GPixel/s; texture rate is 120.0 GTexel/s versus 344.8 GTexel/s; FP32 is 7.680 TFLOPS versus 22.06 TFLOPS; FP16 is 15.36 TFLOPS (2:1) versus 22.06 TFLOPS (1:1). TDP is 80 W versus 160 W. Slot width is IGP versus dual-slot; power connectors are none versus 1x 16-pin; suggested PSU is absent versus 450 W; bus interface is IGP versus PCIe 4.0 x8. Display outputs are portable device dependent versus 1x HDMI 2.1 and 3x DisplayPort 1.4a. The NVIDIA part has physical dimensions of 240 mm by 111 mm by 40 mm, while the Intel part has no listed dimensions. Production status is Active versus End-of-life. Release dates are 2026-01-26 versus 2024-03-31. The NVIDIA part has a launch MSRP of 399 USD, while the Intel part has no listed MSRP. The NVIDIA part lists a predecessor (GeForce 30) and successor (GeForce 50), while the Intel part lists only a predecessor (HD Graphics-WM). The NVIDIA part's memory clock is 2250 MHz (18 Gbps effective), while the Intel part's memory clock is system shared.

The Verdict

The data indicates that the NVIDIA GeForce RTX 4060 Ti AD104 is the stronger performer across every measured compute metric. It delivers 2.87 times the FP32 throughput, 2.03 times the pixel rate, 2.87 times the texture rate, and 2.83 times the ray tracing core count of the Intel Arc Pro B390. It also provides 8 GB of dedicated GDDR6 memory with 288.0 GB/s bandwidth, a resource the Intel part lacks entirely. Users requiring sustained high-resolution gaming, ray-traced rendering, or AI-accelerated workloads should select the NVIDIA part, as its 136 tensor cores and higher core counts provide capabilities the Intel IGP cannot match.

The Intel Arc Pro B390 is the appropriate choice for systems where integration is paramount. Its 80 W TDP, lack of power connectors, and IGP form factor mean it requires no additional cooling or power delivery hardware. The 3 nm process node indicates a modern fabrication approach, and the 2500 MHz boost clock shows it can reach competitive frequencies under load. For portable devices or compact systems where a discrete card is impractical, the Intel part provides a baseline level of graphics capability without the physical footprint or power draw of the NVIDIA card.

The production statuses reinforce this positioning. The NVIDIA GeForce RTX 4060 Ti AD104 is end-of-life, with a successor in the GeForce 50 series already listed. The Intel Arc Pro B390 is active and recently released, suggesting it is the current generation solution for its target platform. The NVIDIA part's 399 USD launch MSRP places it in the discrete mid-range segment, while the Intel part's lack of a listed MSRP reflects its integrated nature, where cost is bundled into the host platform.

The percentile versus all GPUs is identical at 50 for both products, though this metric carries no weight given the zero average benchmark scores and empty benchmark arrays. The absence of head-to-head benchmark entries and nearest rivals means the specification-level comparison stands as the primary evidence. Based on that evidence, the NVIDIA GeForce RTX 4060 Ti AD104 is the higher-performing product by a wide margin, while the Intel Arc Pro B390 offers an integrated, low-power alternative for systems that cannot accommodate a discrete card.