Intel Arc Graphics 1 Xe Mobile vs NVIDIA GeForce RTX 4060 AD106 Comparison

Head-to-Head Benchmarks

The recorded data contains no direct head-to-head benchmark runs between the Intel Arc Graphics 1 Xe Mobile and the NVIDIA GeForce RTX 4060 AD106. Both entries list an empty benchmark array, zero average benchmark scores, and zero wins for either side in the head-to-head section. This means the comparison must be drawn entirely from the specification sheets and the percentile placement, which for both parts sits at the 50th percentile against all GPUs in the database.

The absence of measured scores does not indicate parity. Instead, the specification gap between these two parts is extreme across nearly every compute metric. The Intel part delivers 588.8 GFLOPS of FP32 throughput, while the NVIDIA part delivers 15.11 TFLOPS. That is a 25.7x difference in raw single-precision floating-point performance, a ratio that dwarfs anything seen in typical rival comparisons. The texture rate tells a similar story: the Intel part reaches 18.40 GTexel/s, while the NVIDIA part reaches 236.2 GTexel/s, a 12.8x gap. Pixel throughput differs by an even larger factor, with the Intel part at 9.200 GPixel/s versus 118.1 GPixel/s for the NVIDIA part, a 12.8x difference as well.

The shading unit count reinforces this divide. Intel packs 128 shading units, while NVIDIA uses 3072. The TMU count is 8 versus 96, and the ROP count is 4 versus 48. Each of those structural differences compounds into the final throughput figures listed above. The ray tracing hardware also differs sharply: Intel includes 1 RT core, while NVIDIA includes 24 RT cores. Tensor cores are present on the NVIDIA part at 96, while the Intel part lists none.

Clock speeds narrow the gap slightly but do not close it. The Intel base clock is 300 MHz with a boost of 2300 MHz. The NVIDIA base clock is 1830 MHz with a boost of 2460 MHz. The boost clocks are within 160 MHz of each other, but the NVIDIA part sustains a much higher base clock, which indicates a fundamentally different power and thermal envelope. The TDP figures confirm this: 25 W for the Intel part versus 115 W for the NVIDIA part, a 4.6x difference in power draw.

FP16 throughput shows a notable architectural divergence. The Intel part lists 1,177.6 GFLOPS at a 2:1 ratio, meaning it halves the rate for FP16 versus FP32. The NVIDIA part lists 15.11 TFLOPS at a 1:1 ratio, meaning it sustains the same throughput for FP16 as FP32. This indicates that the NVIDIA architecture is designed for compute workloads that benefit from FP16, while the Intel part is not.

The memory subsystem differs completely. The Intel part uses system shared memory with system dependent bandwidth, while the NVIDIA part uses 8 GB of GDDR6 on a 128-bit bus with 272.0 GB/s of bandwidth. The NVIDIA memory clock runs at 2125 MHz with 17 Gbps effective data rate. The Intel part has no dedicated VRAM, no fixed bus width, and no fixed bandwidth figure, making its memory performance entirely dependent on the host system.

The Verdict

The data points to two entirely different product categories. The Intel Arc Graphics 1 Xe Mobile is an integrated GPU, listed with an IGP slot width, IGP bus interface, no power connectors, and a 25 W TDP. The NVIDIA GeForce RTX 4060 AD106 is a discrete dual-slot card with a 1x 12-pin power connector, a suggested PSU of 300 W, and a 115 W TDP. These are not competing products in the conventional sense.

The Intel part fits into a mobile or ultraportable context where the GPU shares system memory and draws minimal power. Its 128 shading units, 8 TMUs, and 4 ROPs place it at the very low end of the performance spectrum. The NVIDIA part, with 3072 shading units, 96 TMUs, and 48 ROPs, operates in a completely different performance class.

The percentile placement of both at 50th percentile against all GPUs is curious, but with zero benchmark scores recorded, that percentile may reflect the database's default placement rather than measured performance. The raw specification data does not support equal standing.

For workloads that require sustained FP32 compute, high texture throughput, dedicated VRAM, or hardware ray tracing, the NVIDIA part is the only viable choice from the recorded data. For workloads that require minimal power draw, no external power connectors, and integration into a portable device, the Intel part is the only option. The record shows no benchmark wins for either side, so the verdict rests entirely on the specification sheet.

FAQ

Q: Which GPU has higher FP32 performance?

A: The NVIDIA GeForce RTX 4060 AD106 delivers 15.11 TFLOPS of FP32 throughput, while the Intel Arc Graphics 1 Xe Mobile delivers 588.8 GFLOPS, making the NVIDIA part approximately 25.7x faster in this metric.

Q: Do both GPUs support the same graphics APIs?

A: Yes, both list DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 in the recorded data.

Q: What are the power requirements for each GPU?

A: The Intel Arc Graphics 1 Xe Mobile has a TDP of 25 W and uses no power connectors. The NVIDIA GeForce RTX 4060 AD106 has a TDP of 115 W, requires a 1x 12-pin power connector, and has a suggested PSU of 300 W.

Q: How much dedicated video memory does each GPU have?

A: The Intel part uses system shared memory with no dedicated VRAM size listed. The NVIDIA part has 8 GB of GDDR6 memory on a 128-bit bus with 272.0 GB/s bandwidth.

Q: What is the production status of each GPU?

A: The Intel Arc Graphics 1 Xe Mobile is listed as Active production. The NVIDIA GeForce RTX 4060 AD106 is listed as End-of-life.

Q: Which GPU has more ray tracing cores?

A: The NVIDIA GeForce RTX 4060 AD106 has 24 RT cores, while the Intel Arc Graphics 1 Xe Mobile has 1 RT core.

Specification Differences

The two parts differ on nearly every specification field recorded in the database.

The Intel Arc Graphics 1 Xe Mobile uses a 3 nm process node from Intel foundry, while the NVIDIA GeForce RTX 4060 AD106 uses a 5 nm process node from TSMC. The NVIDIA part has a recorded transistor count of 22,900 million and a die size of 188 mm², yielding a transistor density of 121.8M per mm². The Intel part lists transistors and die size as unknown.

Clock speeds differ: the Intel base clock is 300 MHz with a 2300 MHz boost, while the NVIDIA base clock is 1830 MHz with a 2460 MHz boost. The NVIDIA memory clock is 2125 MHz with 17 Gbps effective, while the Intel memory clock is listed as system shared.

Memory configurations are entirely different. The Intel part has system shared size, type, bus width, and system dependent bandwidth. The NVIDIA part has 8 GB GDDR6, a 128-bit bus, and 272.0 GB/s bandwidth.

Compute unit counts differ substantially: 128 shading units versus 3072, 8 TMUs versus 96, 4 ROPs versus 48, 1 RT core versus 24, and no tensor cores versus 96.

Rates differ: the Intel pixel rate is 9.200 GPixel/s versus 118.1 GPixel/s for NVIDIA. The texture rate is 18.40 GTexel/s versus 236.2 GTexel/s. FP32 is 588.8 GFLOPS versus 15.11 TFLOPS. FP16 is 1,177.6 GFLOPS at 2:1 versus 15.11 TFLOPS at 1:1.

TDP differs: 25 W versus 115 W. Slot width is IGP versus dual-slot. Power connectors are none versus 1x 12-pin. The suggested PSU is null for Intel and 300 W for NVIDIA. The bus interface is IGP versus PCIe 4.0 x8. Display outputs are portable device dependent for Intel versus 1x HDMI 2.1 and 3x DisplayPort 1.4a for NVIDIA.

Release dates differ: the Intel part released on 2026-04-15, while the NVIDIA part released on 2024-03-31. The Intel predecessor is HD Graphics-M, while the NVIDIA predecessor is GeForce 30. The NVIDIA successor is GeForce 50, while the Intel successor is null. Production status is Active for Intel and End-of-life for NVIDIA.

Architecture Differences

The architecture records show a fundamental design split. The Intel part uses the Xe3-LPG architecture on the Wildcat Lake chip, belonging to the Arc Graphics-M generation. The NVIDIA part uses the Ada Lovelace architecture on the AD106 chip, belonging to the GeForce 40 series.

The Intel process node is 3 nm at Intel foundry, while the NVIDIA process node is 5 nm at TSMC. The Intel chip has unknown transistor count and die size, while the NVIDIA chip has 22,900 million transistors on a 188 mm² die, giving a density of 121.8M per mm².

The FP16 implementation differs: Intel lists 1,177.6 GFLOPS at a 2:1 ratio, while NVIDIA lists 15.11 TFLOPS at a 1:1 ratio. This indicates the Intel architecture uses a packed FP16 path that halves throughput, while the NVIDIA architecture maintains full rate.

Ray tracing hardware differs: 1 RT core on Intel versus 24 on NVIDIA. Tensor cores exist only on the NVIDIA part, with 96 of them. The Intel part has no tensor core listing.

The memory architecture is fundamentally different: Intel uses system shared memory with system dependent bandwidth, while NVIDIA uses dedicated GDDR6 with fixed 272.0 GB/s bandwidth. This affects how each part accesses data and what workloads they can handle.

The bus interface reflects the integration level: Intel uses IGP, while NVIDIA uses PCIe 4.0 x8. The Intel part has no power connectors and a 25 W TDP, indicating it draws power from the host system. The NVIDIA part requires a 1x 12-pin connector and a 300 W suggested PSU.

Where Each One Wins

The Intel Arc Graphics 1 Xe Mobile wins in power efficiency and integration. Its 25 W TDP is 4.6x lower than the NVIDIA part's 115 W. It requires no power connectors, no external PSU, and uses an IGP bus interface, making it suitable for portable devices where space and power are constrained. Its 3 nm process node from Intel foundry is a smaller node than the NVIDIA 5 nm TSMC node, which contributes to its lower power draw. The display outputs are portable device dependent, meaning it adapts to whatever screen is built into the host system.

The NVIDIA GeForce RTX 4060 AD106 wins in every raw performance metric recorded. Its 15.11 TFLOPS FP32 is 25.7x higher than the Intel part. Its 236.2 GTexel/s texture rate is 12.8x higher. Its 118.1 GPixel/s pixel rate is 12.8x higher. It has 24x more shading units, 12x more TMUs, 12x more ROPs, and 24x more RT cores. It has 96 tensor cores that the Intel part lacks entirely. Its 8 GB GDDR6 memory with 272.0 GB/s bandwidth provides dedicated, high-speed memory access that the Intel part cannot match with system shared memory.

The NVIDIA part supports FP16 at full rate, making it viable for workloads that use FP16 compute. The Intel part halves FP16 throughput, limiting its usefulness in those scenarios. The NVIDIA part has a fixed memory bandwidth of 272.0 GB/s, while the Intel part's bandwidth is system dependent, meaning its memory performance varies with the host platform.

The production status also differs: the Intel part is Active, while the NVIDIA part is End-of-life. This suggests the Intel part is currently in production, while the NVIDIA part has been discontinued. The release dates reflect this, with the Intel part released on 2026-04-15 and the NVIDIA part on 2024-03-31.

The data shows no benchmark wins for either side, so the use-case split is based entirely on the specification differences. The Intel part suits low-power, integrated, portable scenarios. The NVIDIA part suits high-performance, discrete, desktop scenarios with dedicated power delivery and cooling.