Intel Iris Xe MAX Graphics vs NVIDIA GeForce GTX 1070 Ti Comparison

Intel Iris Xe MAX Graphics and NVIDIA GeForce GTX 1070 Ti are both end-of-life products, but they represent vastly different approaches to graphics processing. The data places them in the same performance tier according to aggregate scores, yet a single head-to-head benchmark reveals a dramatic gap. The GTX 1070 Ti holds a percentile rank of 56, while the Iris Xe MAX also sits at 56, indicating similar standing against all GPUs in the database. However, their architectural and physical differences are stark, making them suited for entirely different systems and workloads.

Head-to-Head Benchmarks

The only direct benchmark comparison available is Geekbench OpenCL, and the results are decisively one-sided. The NVIDIA GeForce GTX 1070 Ti scores 49,219 points, while the Intel Iris Xe MAX Graphics manages 14,315 points. This represents a 70.9% deficit for the Intel part relative to the NVIDIA card. In practical terms, the GTX 1070 Ti delivers over three times the raw compute throughput in this test, making it the clear winner in this specific metric.

This single result dominates the head-to-head record, giving the GTX 1070 Ti one win and the Iris Xe MAX zero. It is important to note that these scores come from different test suites, and the Geekbench OpenCL test is particularly sensitive to raw shader throughput and memory bandwidth. The GTX 1070 Ti’s 8.186 TFLOPS of FP32 performance and 256.3 GB/s bandwidth are the likely drivers of this outcome, while the Iris Xe MAX’s 2.534 TFLOPS and 68.26 GB/s bandwidth place it far behind in this compute-oriented workload.

When looking at the broader context, the average benchmark scores tell a different story. The Iris Xe MAX has an average score of 14,315, while the GTX 1070 Ti averages 14,277. This puts the Intel part 0.3% ahead of the NVIDIA part in their respective averages, a negligible difference that suggests the GTX 1070 Ti’s massive OpenCL advantage is offset by other factors in its benchmark suite. The GTX 1070 Ti’s other scores—such as 14,674 in Passmark G3D and 61,006 in Geekbench Vulkan—show strength in different areas, but the Iris Xe MAX only has the one OpenCL result, which drags its average down.

Architecture Differences

The two GPUs are built on fundamentally different foundations. The Intel Iris Xe MAX uses the DG1 chip, based on the Generation 12.1 architecture, which is part of the Xe Graphics generation. It is fabricated on a 10 nm process by Intel itself, with a die size of 95 mm². In contrast, the NVIDIA GeForce GTX 1070 Ti uses the GP104 chip, based on the older Pascal architecture from the GeForce 10 series. This chip is built on a 16 nm process by TSMC, with a much larger die size of 314 mm² and 7,200 million transistors.

The transistor density highlights the process advantage for Intel: the Iris Xe MAX packs its logic into a smaller space, while the GTX 1070 Ti’s larger die allows for more raw hardware. The NVIDIA part has 2,432 shading units, 152 texture mapping units, and 64 raster output units. The Intel part has 768 shading units, 48 TMUs, and 24 ROPs. This massive difference in core counts explains why the GTX 1070 Ti achieves much higher pixel and texture rates—107.7 GPixel/s and 255.8 GTexel/s, respectively—compared to the Iris Xe MAX’s 39.60 GPixel/s and 79.20 GTexel/s.

Memory configurations also diverge sharply. The Iris Xe MAX uses 4 GB of LPDDR4X on a 128-bit bus, delivering 68.26 GB/s of bandwidth. The GTX 1070 Ti uses 8 GB of GDDR5 on a 256-bit bus, delivering 256.3 GB/s. Clock speeds tell a similar story: the Intel part boosts to 1650 MHz from a 300 MHz base, while the NVIDIA part boosts to 1683 MHz from a 1607 MHz base. Notably, the Iris Xe MAX has a 2:1 FP16 ratio, offering 5.069 TFLOPS of half-precision performance, while the GTX 1070 Ti has a 1:64 ratio, yielding only 127.9 GFLOPS of FP16—a massive difference in compute precision capability.

Where Each One Wins

The GTX 1070 Ti wins decisively in raw compute and gaming-oriented workloads. Its Geekbench OpenCL score is 3.4 times higher than the Iris Xe MAX, and its Passmark DirectX 11 score of 107 versus the Intel part’s absence of any DirectX benchmark suggests it is built for sustained performance under load. The NVIDIA card also has a 180 W TDP and requires a 450 W power supply, indicating it is designed for desktop systems with dedicated power delivery. Its dual-slot form factor and 267 mm length make it a standard add-in card, with display outputs including 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a, allowing it to drive multiple monitors directly.

The Iris Xe MAX, by contrast, is an integrated graphics processor (IGP) with a 25 W TDP and a suggested power supply of only 200 W. It has no display outputs, meaning it is not a standalone card but rather a component for a system with a separate display connection. Its 10 nm process and 95 mm² die size suggest it is intended for compact, power-efficient devices. The data does not show any benchmark wins for the Intel part, but its 0.3% aggregate score advantage over the GTX 1070 Ti implies that in some unspecified workloads, it can match or slightly exceed the NVIDIA part. The FP16 capability is a notable strength, offering more than 40 times the half-precision throughput of the GTX 1070 Ti, which could be relevant for compute tasks that leverage mixed precision.

For practical use, the GTX 1070 Ti is the clear choice for gaming and heavy graphics workloads, given its higher memory capacity, bandwidth, and shader throughput. The Iris Xe MAX, with its low power draw and integrated nature, would be better suited for thin-and-light laptops or low-power desktops where space and heat are constrained, provided the workload does not rely on the strengths of a discrete GPU.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The Intel Iris Xe MAX Graphics has an average benchmark score of 14,315, which is 0.3% higher than the NVIDIA GeForce GTX 1070 Ti’s average score of 14,277.

Q: What is the performance difference in the Geekbench OpenCL test?

A: The GTX 1070 Ti scores 49,219 points, while the Iris Xe MAX scores 14,315 points. This gives the NVIDIA card a 70.9% advantage over the Intel part.

Q: How much memory does each GPU have?

A: The Intel Iris Xe MAX Graphics has 4 GB of LPDDR4X memory, while the NVIDIA GeForce GTX 1070 Ti has 8 GB of GDDR5 memory.

Q: What is the TDP of each GPU?

A: The Intel Iris Xe MAX Graphics has a TDP of 25 W, whereas the NVIDIA GeForce GTX 1070 Ti has a TDP of 180 W.

Q: Which GPU supports a higher FP16 throughput?

A: The Intel Iris Xe MAX Graphics supports 5.069 TFLOPS of FP16 performance with a 2:1 ratio, while the NVIDIA GeForce GTX 1070 Ti supports only 127.9 GFLOPS with a 1:64 ratio.

Q: What are the process nodes for each GPU?

A: The Intel Iris Xe MAX Graphics is built on a 10 nm process, while the NVIDIA GeForce GTX 1070 Ti is built on a 16 nm process.

Specification Differences

The two GPUs differ across nearly every specification. The Intel Iris Xe MAX uses the DG1 chip on a 10 nm process from Intel, with a 95 mm² die size and no listed transistor count. The NVIDIA GTX 1070 Ti uses the GP104 chip on a 16 nm process from TSMC, with a 314 mm² die size and 7,200 million transistors. Clock speeds are close in boost (1650 MHz for Intel, 1683 MHz for NVIDIA), but base clocks differ widely: 300 MHz versus 1607 MHz.

Memory is another major divergence: the Iris Xe MAX has 4 GB of LPDDR4X on a 128-bit bus with 68.26 GB/s bandwidth, while the GTX 1070 Ti has 8 GB of GDDR5 on a 256-bit bus with 256.3 GB/s bandwidth. The NVIDIA card has 2432 shading units, 152 TMUs, and 64 ROPs, compared to the Intel part’s 768 shading units, 48 TMUs, and 24 ROPs. Pixel and texture rates favor NVIDIA massively: 107.7 GPixel/s versus 39.60 GPixel/s, and 255.8 GTexel/s versus 79.20 GTexel/s. FP32 performance is 8.186 TFLOPS for NVIDIA versus 2.534 TFLOPS for Intel, but FP16 performance reverses, with Intel at 5.069 TFLOPS and NVIDIA at 127.9 GFLOPS.

Power and physical design differ as well. The Iris Xe MAX has a 25 W TDP, is an IGP with no power connectors, and requires a 200 W power supply. The GTX 1070 Ti has a 180 W TDP, is a dual-slot card with a 1x 8-pin connector, and requires a 450 W power supply. The Intel part has no display outputs, while the NVIDIA card has 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a. The NVIDIA card is 267 mm long, 112 mm tall, and 40 mm wide, whereas the Intel part has no listed dimensions. Bus interfaces also differ: PCIe 4.0 x8 for Intel versus PCIe 3.0 x16 for NVIDIA. Release dates are nearly three years apart, with the Iris Xe MAX launching on 2020-10-30 and the GTX 1070 Ti on 2017-11-01. The GTX 1070 Ti has a launch MSRP of 399 USD.

The Verdict

The data makes a clear case for the NVIDIA GeForce GTX 1070 Ti in most scenarios. It dominates the only head-to-head benchmark with a 70.9% lead in Geekbench OpenCL, and its 8 GB of memory and 256.3 GB/s bandwidth are far superior for modern gaming and content creation. Its 8.186 TFLOPS of FP32 power and 107.7 GPixel/s pixel rate confirm it is a serious performer for rasterized workloads. The GTX 1070 Ti is the pick for anyone building a desktop system that requires a dedicated graphics card with direct display outputs and sustained high performance.

The Intel Iris Xe MAX Graphics, however, has a niche. Its 25 W TDP and IGP form factor make it suitable for low-power systems where a discrete card is not feasible. Its FP16 performance of 5.069 TFLOPS is a standout feature, outperforming the GTX 1070 Ti by over 40 times in that specific precision, which could appeal to compute-oriented tasks that use half-precision arithmetic. Its 0.3% aggregate score advantage over the GTX 1070 Ti is statistically negligible, but it shows that in some tests, the Intel part is competitive.

For a builder prioritizing raw graphics performance, the GTX 1070 Ti is the only logical choice, despite its higher power draw and larger physical footprint. For a user with power constraints or a compact system, the Iris Xe MAX offers a unique set of capabilities, but its lack of display outputs and limited memory capacity mean it cannot replace a discrete GPU. The verdict is simple: buy the GTX 1070 Ti for gaming and rendering; consider the Iris Xe MAX only for specialized low-power compute workloads.