Intel Iris Xe MAX Graphics vs NVIDIA GeForce GTX 1660 SUPER Comparison

Intel Iris Xe MAX Graphics and NVIDIA GeForce GTX 1660 SUPER occupy very different positions in the recorded benchmark database. The Iris Xe MAX is a low-power integrated-class part from Intel’s Xe Graphics generation, built on the DG1 chip. The GTX 1660 SUPER is a dedicated dual-slot add-in card from NVIDIA’s GeForce 16 series, using the TU116 chip. Their measured performance gap is large, but the database also reveals where each part justifies its existence.

The Verdict

The database records a single shared benchmark between these two GPUs: Geekbench OpenCL. In that test, the NVIDIA GeForce GTX 1660 SUPER scores 52,490, while the Intel Iris Xe MAX Graphics scores 14,315. That is a 72.7% deficit for the Intel part relative to the NVIDIA card. The GTX 1660 SUPER wins the only head-to-head comparison, and it wins by a wide margin.

The GTX 1660 SUPER is the clear choice for any workload that demands raw compute throughput, higher memory bandwidth, or sustained rendering performance. Its average benchmark score across all recorded tests is 12,986, which places it at the 53rd percentile of all GPUs in the database. The Iris Xe MAX has an average benchmark score of 14,315 from a single test, placing it at the 56th percentile. However, that percentile is misleading in context: the Iris Xe MAX’s only score comes from a single OpenCL run, while the GTX 1660 SUPER’s average includes multiple DirectX and compute workloads. The NVIDIA card’s nearest rivals include the RTX 3050 Ti Mobile (0.4% ahead), the RX 580 (0.4% ahead), and the AMD Radeon 740M (0.9% behind). The Iris Xe MAX sits near the AMD Radeon Vega 11 (0.3% behind) and the GTX 1070 Ti (0.3% ahead). In practical terms, the GTX 1660 SUPER competes with mainstream desktop GPUs, while the Iris Xe MAX trades blows with integrated Vega-class parts.

For a user who needs a working GPU with no external power connectors and minimal cooling requirements, the Iris Xe MAX is the only option here. For anyone who has a PCIe slot, a power supply with an 8-pin connector, and a need for real gaming or compute performance, the GTX 1660 SUPER is the only sensible pick.

Architecture Differences

The Intel Iris Xe MAX is built on a 10 nm process at Intel’s foundry, with a die size of 95 mm². The GTX 1660 SUPER uses a 12 nm process at TSMC, with a much larger die of 284 mm² and 6,600 million transistors. The transistor density of the NVIDIA chip is recorded at 23.2M per mm². The Intel part has no transistor count listed, but its smaller die and integrated nature suggest a lower absolute transistor budget.

The Iris Xe MAX uses LPDDR4X memory with a 128-bit bus and 68.26 GB/s bandwidth. The GTX 1660 SUPER uses GDDR6 with a 192-bit bus and 336.0 GB/s bandwidth, nearly five times the memory bandwidth. The Intel part has 4 GB of memory, the NVIDIA card has 6 GB. The Iris Xe MAX’s memory runs at 2133 MHz (4.3 Gbps effective), while the GTX 1660 SUPER’s memory runs at 1750 MHz (14 Gbps effective).

The Intel GPU has 768 shading units, 48 texture mapping units, and 24 raster operation units. The NVIDIA card has 1,408 shading units, 88 TMUs, and 48 ROPs. The GTX 1660 SUPER has roughly 83% more shading units, 83% more TMUs, and double the ROPs. The pixel rate of the NVIDIA card is 85.68 GPixel/s versus 39.60 GPixel/s for Intel. The texture rate is 157.1 GTexel/s versus 79.20 GTexel/s. FP32 compute is 5.027 TFLOPS for NVIDIA and 2.534 TFLOPS for Intel. FP16 is 10.05 TFLOPS (2:1) for NVIDIA and 5.069 TFLOPS (2:1) for Intel.

The Iris Xe MAX has a base clock of 300 MHz and a boost clock of 1650 MHz. The GTX 1660 SUPER has a base clock of 1530 MHz and a boost of 1785 MHz. The Intel part is rated at 25 W TDP, while the NVIDIA card is rated at 125 W. The Intel GPU uses a PCIe 4.0 x8 interface, the NVIDIA card uses PCIe 3.0 x16. The Iris Xe MAX has no display outputs, meaning it cannot drive a monitor on its own. The GTX 1660 SUPER offers 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a.

Both support DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. Neither has dedicated ray tracing or tensor cores. The Intel part is listed as end-of-life, with a successor named Alchemist. The NVIDIA card is also end-of-life, with a predecessor of GeForce 10 and successor of GeForce 20.

Head-to-Head Benchmarks

The database records exactly one direct comparison: Geekbench OpenCL. The GTX 1660 SUPER scores 52,490, the Iris Xe MAX scores 14,315. The percentage difference is -72.7% for the Intel part, meaning the NVIDIA card outperforms it by nearly four times in raw OpenCL compute.

That single result is consistent with the underlying specifications. The GTX 1660 SUPER has roughly twice the FP32 throughput (5.027 vs 2.534 TFLOPS), nearly five times the memory bandwidth (336.0 vs 68.26 GB/s), and double the ROP count (48 vs 24). The Iris Xe MAX has a much higher boost clock relative to its base (1650 MHz vs 300 MHz), but that cannot compensate for fewer execution units and a narrow memory bus.

The GTX 1660 SUPER’s additional benchmark results show a varied profile. In Passmark G3D, it scores 12,699. In Passmark GPU Compute, it scores 5,076. In Geekbench Vulkan, it scores 57,102. In 3DMark Steel Nomad DX12, it scores 1,278. Its DirectX 9 and DirectX 11 Passmark scores are 189 and 104 respectively, while DirectX 10 and DirectX 12 scores are 65 and 50. The Iris Xe MAX has no recorded results in any of these tests, so the only apples-to-apples comparison is the OpenCL run.

The GTX 1660 SUPER’s average benchmark score of 12,986 is pulled down by its low Passmark DirectX scores, but those tests are not representative of its overall capability. The Intel part’s average of 14,315 comes from a single high OpenCL score, which inflates its percentile ranking relative to the NVIDIA card. In the database’s percentile distribution, the Iris Xe MAX ranks at 56, the GTX 1660 SUPER at 53, yet the GTX 1660 SUPER is clearly the faster GPU in the head-to-head measurement.

FAQ

Q: Which GPU has higher memory bandwidth?

A: The NVIDIA GeForce GTX 1660 SUPER has 336.0 GB/s bandwidth, while the Intel Iris Xe MAX has 68.26 GB/s.

Q: Can the Intel Iris Xe MAX output video to a monitor?

A: No. The database lists “No outputs” for display outputs on the Intel part. The GTX 1660 SUPER has 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a.

Q: What is the power draw difference?

A: The Intel Iris Xe MAX is rated at 25 W TDP, the NVIDIA GTX 1660 SUPER at 125 W TDP. The suggested PSU for Intel is 200 W, for NVIDIA it is 300 W.

Q: Which GPU has more shading units?

A: The GTX 1660 SUPER has 1,408 shading units, the Iris Xe MAX has 768.

Q: Are both GPUs end-of-life products?

A: Yes. The Intel Iris Xe MAX is listed as end-of-life with successor Alchemist. The GTX 1660 SUPER is also end-of-life, with predecessor GeForce 10 and successor GeForce 20.

Q: What is the only shared benchmark result?

A: Geekbench OpenCL. The GTX 1660 SUPER scores 52,490, the Iris Xe MAX scores 14,315, a 72.7% difference.

Where Each One Wins

The GTX 1660 SUPER wins every measurable category in the database. It has higher FP32 compute (5.027 vs 2.534 TFLOPS), higher FP16 compute (10.05 vs 5.069 TFLOPS), higher pixel rate (85.68 vs 39.60 GPixel/s), higher texture rate (157.1 vs 79.20 GTexel/s), more memory (6 GB vs 4 GB), faster memory type (GDDR6 vs LPDDR4X), wider memory bus (192-bit vs 128-bit), and more than double the memory bandwidth (336.0 vs 68.26 GB/s). It also has more TMUs (88 vs 48) and ROPs (48 vs 24).

The GTX 1660 SUPER is the appropriate choice for any workload that stresses compute, such as 3D rendering, GPU-accelerated video encoding, or gaming at high resolutions. Its nearest rival in the database is the RTX 3050 Ti Mobile, which is only 0.4% ahead, so the GTX 1660 SUPER sits at the top of its performance class among recorded desktop GPUs.

The Iris Xe MAX wins only in the attributes that favor integration: lower TDP (25 W vs 125 W), smaller die (95 mm² vs 284 mm²), and no external power connector requirement (the GTX 1660 SUPER needs 1x 8-pin). It also uses a PCIe 4.0 x8 interface, while the NVIDIA card uses PCIe 3.0 x16. The Intel part is an IGP (integrated graphics package) with no display outputs, meaning it is designed for a system that already has a separate display path, likely a laptop or an embedded platform.

For a user who needs GPU compute in a power-constrained environment, the Iris Xe MAX is the only part that fits. For a desktop user with a standard power supply and a PCIe slot, the GTX 1660 SUPER is overwhelmingly faster in every recorded benchmark.

Specification Differences

The following fields differ between the two parts:

• Process node: Intel 10 nm vs NVIDIA 12 nm
• Foundry: Intel vs TSMC
• Die size: 95 mm² vs 284 mm²
• Transistors: Not listed vs 6,600 million
• Transistor density: Not listed vs 23.2M / mm²
• Base clock: 300 MHz vs 1530 MHz
• Boost clock: 1650 MHz vs 1785 MHz
• Memory clock: 2133 MHz (4.3 Gbps effective) vs 1750 MHz (14 Gbps effective)
• Memory size: 4 GB vs 6 GB
• Memory type: LPDDR4X vs GDDR6
• Memory bus: 128-bit vs 192-bit
• Memory bandwidth: 68.26 GB/s vs 336.0 GB/s
• Shading units: 768 vs 1,408
• TMUs: 48 vs 88
• ROPs: 24 vs 48
• Pixel rate: 39.60 GPixel/s vs 85.68 GPixel/s
• Texture rate: 79.20 GTexel/s vs 157.1 GTexel/s
• FP32: 2.534 TFLOPS vs 5.027 TFLOPS
• FP16: 5.069 TFLOPS vs 10.05 TFLOPS
• TDP: 25 W vs 125 W
• Slot width: IGP vs Dual-slot
• Power connectors: None vs 1x 8-pin
• Suggested PSU: 200 W vs 300 W
• Bus interface: PCIe 4.0 x8 vs PCIe 3.0 x16
• Display outputs: No outputs vs 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a
• Dimensions: Not listed vs 229 mm (9 inches) length, 111 mm (4.4 inches) height, 35 mm (1.4 inches) width
• Release date: 2020-10-30 vs 2019-10-28
• Predecessor: Graphics vs GeForce 10
• Successor: Alchemist vs GeForce 20
• Launch MSRP: Not listed vs 229 USD (stated once as launch MSRP)

The GTX 1660 SUPER also has a larger set of recorded benchmarks, including 3DMark Steel Nomad DX12, Passmark DirectX 9/10/11/12, Passmark G2D, Passmark G3D, and Passmark GPU Compute. The Iris Xe MAX has only Geekbench OpenCL. The NVIDIA card’s average benchmark score is 12,986, while the Intel part’s is 14,315, but that average includes many lower-scoring legacy tests. The database’s percentile ranking puts the Iris Xe MAX at 56 and the GTX 1660 SUPER at 53, yet the head-to-head result shows a 72.7% advantage for the NVIDIA product.