Intel Iris Xe MAX Graphics vs NVIDIA GeForce GTX 770 Comparison

The Verdict

The data presents a clear but narrow outcome: the NVIDIA GeForce GTX 770 wins the only head-to-head benchmark available, beating the Intel Iris Xe MAX Graphics in Geekbench OpenCL by 9.7%. That single victory gives the GTX 770 a 1–0 win record in direct comparisons. However, the broader picture is far closer than the name brands suggest. The GTX 770 averages 14,747 points across all benchmarks, while the Iris Xe MAX averages 14,315 — a gap of roughly 3%. The GTX 770 sits at the 57th percentile of all GPUs, the Iris Xe MAX at the 56th, meaning both are mid-pack parts with nearly identical standing.

For anyone building a desktop with an available PCIe slot and a 550 W power supply, the GTX 770 is the safer pick for raw compute throughput, especially in OpenCL workloads. Its 3.333 TFLOPS FP32 output and 224.4 GB/s memory bandwidth give it a structural edge that shows in the benchmark delta. For anyone needing a low-power, integrated solution — the Iris Xe MAX draws just 25 W versus 230 W and needs no power connectors — the Intel part is the only realistic option despite its lower raw scores. The GTX 770 is end-of-life, dual-slot, 267 mm long, and requires both a 6-pin and an 8-pin connector; the Iris Xe MAX is an IGP with no outputs of its own, so it only makes sense in a system where the CPU already provides display connectivity. Choose the GTX 770 for compute headroom, choose the Iris Xe MAX for efficiency and integration.

Architecture Differences

These two GPUs come from opposite ends of the hardware spectrum, separated by seven years of process evolution. The GTX 770 uses NVIDIA's Kepler architecture on a 28 nm TSMC process, packing 3,540 million transistors into a 294 mm² die. That works out to a transistor density of 12.0 million per square millimeter. The Iris Xe MAX uses Intel's Generation 12.1 Xe architecture on a 10 nm Intel process, with a die size of just 95 mm² — transistor count is not listed, but the density is clearly far higher given the smaller die and newer node.

The compute resources differ sharply. The GTX 770 fields 1,536 shading units, 128 texture mapping units, and 32 ROPs. The Iris Xe MAX has 768 shading units, 48 TMUs, and 24 ROPs — exactly half the shaders, just over a third of the TMUs, and three-quarters of the ROPs. Yet the pixel rates tell a different story: the Iris Xe MAX achieves 39.60 GPixel/s, slightly ahead of the GTX 770's 34.72 GPixel/s, thanks to its much higher boost clock of 1650 MHz versus 1085 MHz. The texture rate favors the GTX 770 at 138.9 GTexel/s versus 79.20 GTexel/s.

Memory is another major divider. The GTX 770 uses 2 GB of GDDR5 on a 256-bit bus, delivering 224.4 GB/s of bandwidth. The Iris Xe MAX uses 4 GB of LPDDR4X on a 128-bit bus, delivering only 68.26 GB/s. That 3.3x bandwidth advantage is the GTX 770's most significant structural lead. Clock speeds also differ dramatically: the GTX 770 runs at a 1046 MHz base and 1085 MHz boost, while the Iris Xe MAX idles at 300 MHz base and ramps to 1650 MHz boost. The Iris Xe MAX supports DirectX 12 (12_1) and Vulkan 1.4, while the GTX 770 is limited to DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6. The GTX 770 has no FP16 support listed; the Iris Xe MAX does FP16 at 5.069 TFLOPS with a 2:1 ratio.

Where Each One Wins

The GTX 770 wins in every category where raw throughput matters. Its FP32 compute of 3.333 TFLOPS beats the Iris Xe MAX's 2.534 TFLOPS by a clear margin. Its texture rate of 138.9 GTexel/s is 75% higher. Its memory bandwidth of 224.4 GB/s is more than triple the Intel part's 68.26 GB/s. The Geekbench OpenCL score reflects this: 15,707 versus 14,315, a 9.7% victory for NVIDIA. The GTX 770 also supports more display outputs — 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2 — making it a functional standalone graphics card.

The Iris Xe MAX wins where efficiency and integration matter. It draws 25 W versus 230 W, a 9.2x reduction in power consumption. It needs no power connectors, while the GTX 770 requires a 6-pin and an 8-pin. Its suggested PSU is 200 W, versus 550 W for the GTX 770. The Iris Xe MAX is an IGP with zero display outputs, meaning it relies on the host CPU for video output — an architectural choice that makes it invisible in a desktop build but ideal for compact systems. It also has double the memory capacity at 4 GB, though with a narrower bus and slower speed. Its pixel rate of 39.60 GPixel/s edges out the GTX 770's 34.72 GPixel/s, a rare win for Intel in raw rasterization throughput. The Iris Xe MAX also supports newer API features: DirectX 12_1 and Vulkan 1.4, versus the GTX 770's 11_0 and 1.2.175.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 770 averages 14,747 points across all benchmarks, while the Intel Iris Xe MAX averages 14,315 points. The GTX 770's nearest rival is the AMD Radeon RX 5500 XT at 14,692 points (0.4% higher), while the Iris Xe MAX's closest competitor is the AMD Radeon Vega 11 at 14,352 points (0.3% lower than Intel).

Q: How much faster is the GTX 770 in the only head-to-head test?

A: In Geekbench OpenCL, the GTX 770 scores 15,707 versus the Iris Xe MAX's 14,315, a delta of 9.7% in NVIDIA's favor. This is the sole direct benchmark comparison available between the two.

Q: What is the power requirement difference?

A: The GTX 770 has a TDP of 230 W and a suggested PSU of 550 W, requiring one 6-pin and one 8-pin power connector. The Iris Xe MAX has a TDP of 25 W and a suggested PSU of 200 W, with no power connectors needed at all.

Q: Does the Iris Xe MAX have any performance advantage?

A: Yes. Its pixel rate is 39.60 GPixel/s, slightly ahead of the GTX 770's 34.72 GPixel/s. It also has 4 GB of memory versus 2 GB, though its bandwidth is far lower at 68.26 GB/s versus 224.4 GB/s.

Q: Which GPU supports newer graphics APIs?

A: The Intel Iris Xe MAX supports DirectX 12 (12_1) and Vulkan 1.4, while the NVIDIA GTX 770 supports DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6.

Q: What is the form factor difference?

A: The GTX 770 is a dual-slot, 267 mm long, 111 mm high, 38 mm wide card. The Iris Xe MAX is an IGP with no physical dimensions listed, no display outputs, and no slot width — it is integrated into the system.

Head-to-Head Benchmarks

The only direct benchmark comparison in the data is Geekbench OpenCL, and it confirms the expected hierarchy. The GTX 770 scores 15,707, the Iris Xe MAX scores 14,315, and NVIDIA wins by 9.7%. That margin is significant but not overwhelming — it places the GTX 770 in a different performance class, but only by a single step.

To contextualize that delta, look at the nearest rivals. The GTX 770's average score of 14,747 puts it 0.4% behind the AMD Radeon RX 5500 XT (14,692) — essentially a tie. It is 1.5% ahead of the NVIDIA Quadro M2000 (14,532) and 2.1% behind the GeForce GTX 660 Ti (15,063). The Iris Xe MAX's average of 14,315 sits 0.3% below the Radeon Vega 11 (14,352) and 0.3% above the GeForce GTX 1070 Ti (14,277) — again, a dead heat with a much more powerful-sounding card. The GTX TITAN is 0.4% above Intel's part at 14,373.

The interesting twist is that the Iris Xe MAX's average score is dragged down by having only one benchmark result, while the GTX 770 has three (Geekbench Metal at 9,369, OpenCL at 15,707, Vulkan at 19,166). That Vulkan score of 19,166 is the GTX 770's best result and likely inflates its average relative to its OpenCL-only comparison with Intel. If the head-to-head were limited to OpenCL, the GTX 770 would still win, but the average gap would shrink to 9.7% — the same as the single benchmark delta.

The pixel rate comparison is worth noting for rasterization-heavy tasks. The Iris Xe MAX hits 39.60 GPixel/s, beating the GTX 770's 34.72 GPixel/s despite having only 24 ROPs versus 32. That is a 14% advantage for Intel in fill-rate-limited scenarios, likely due to the 1650 MHz boost clock versus 1085 MHz. However, in texture-heavy workloads, the GTX 770's 138.9 GTexel/s versus 79.20 GTexel/s gives it a 75% lead, and in memory-bound tasks, the 224.4 GB/s versus 68.26 GB/s is a 3.3x blowout.

Bottom line from the head-to-head data: the GTX 770 wins the compute benchmark decisively but not overwhelmingly, and the Iris Xe MAX holds its own in specific rasterization metrics. The 9.7% OpenCL delta is the single most important number here, and it favors the older, hungrier NVIDIA card.