Intel UHD Graphics P630 vs NVIDIA GeForce GTX 970M Comparison

The Intel UHD Graphics P630 and the NVIDIA GeForce GTX 970M occupy very different positions in the mobile graphics landscape. The P630 is an integrated solution built into Intel’s Comet Lake processors, designed for basic display output and light workloads. The GTX 970M is a dedicated mobile GPU from NVIDIA’s Maxwell 2.0 generation, aimed at gaming and content creation on laptops. The benchmark database shows a clear performance gap, but the nature of that gap and its implications for real-world use deserve a closer look.

Head-to-Head Benchmarks

The recorded head-to-head results cover two modern API tests: Geekbench OpenCL and Geekbench Vulkan. In both, the NVIDIA GeForce GTX 970M delivers decisively higher scores. In the Geekbench OpenCL test, the GTX 970M scores 18,946 points against the Intel UHD Graphics P630’s 5,111 points. That represents a 73% advantage for NVIDIA. The margin is slightly narrower in Geekbench Vulkan, where the GTX 970M scores 18,292 versus the Intel part’s 5,628, a 69.2% lead.

These are not marginal wins. The GTX 970M roughly triples the integrated GPU’s output in both compute and graphics workloads. For context, the Intel UHD Graphics P630’s average benchmark score across all recorded tests is 5,370 points, while the GTX 970M averages 4,628 points. That apparent contradiction, where the GTX 970M has a lower average but wins the head-to-head tests, comes from the different test sets. The GTX 970M has far more recorded benchmarks, including older DirectX 9 and DirectX 10 tests where its scores are comparatively low, dragging down its average. The Intel part only has two Geekbench entries, both of which are its strongest results.

Looking at the percentile rankings, the GTX 970M sits at the 27th percentile of all GPUs in the database, while the Intel UHD Graphics P630 sits at the 31st percentile. Despite the GTX 970M’s dominance in the head-to-head tests, its broader benchmark suite includes legacy API tests that hurt its overall standing. The Intel part benefits from a smaller, more modern test set. Still, when both are tested under the same conditions, the GeForce GTX 970M is clearly the faster product.

Where Each One Wins

The Intel UHD Graphics P630 has no recorded benchmark wins against the GTX 970M. In the two tests where they appear side by side, the NVIDIA part wins both. However, the P630 does hold its own against other low-end mobile GPUs in the database. Its nearest rivals include the AMD Radeon R7 M445, which scores 5,358 points on average, a 0.2% difference from the Intel part. The NVIDIA GeForce 840M averages 5,322 points, putting it 0.9% behind the P630. The NVIDIA GeForce 930A trails by 1%. Only the AMD Radeon R7 M365X edges ahead, with an average score of 5,416, which is 0.8% higher than the Intel integrated solution.

This tells a practical story. The Intel UHD Graphics P630 is competitive with entry-level discrete GPUs from several generations ago. It can handle everyday desktop tasks, video playback, and light productivity software. It is not built for gaming or heavy 3D rendering. The GTX 970M, by contrast, sits in a different class entirely. Its nearest rivals in the database include the NVIDIA Quadro M3000M, which averages 4,621 points, a 0.2% difference, and the AMD Radeon R5 M320 at 4,657 points, which is 0.6% behind. The AMD Radeon RX 9060 XT 16 GB also appears as a rival with the same 4,657 average score.

The GTX 970M’s strength lies in sustained GPU workloads. Its 1280 shading units, 80 texture mapping units, and 48 raster output pipelines give it the raw throughput needed for modern games, video editing, and GPU-accelerated rendering. The Intel P630, with only 192 shading units, 24 TMUs, and 3 ROPs, is fundamentally limited. It wins in power efficiency and simplicity, but not in performance.

Architecture Differences

The two GPUs come from entirely different design philosophies. The Intel UHD Graphics P630 uses Intel’s Generation 9.5 architecture, built on a 14 nm+++ process node at Intel’s own fabs. Its chip is designated Comet Lake GT2. The GTX 970M uses NVIDIA’s Maxwell 2.0 architecture, fabricated by TSMC on a 28 nm process. The chip is GM204, and it contains 5,200 million transistors on a 398 mm² die. That gives a transistor density of 13.1 million transistors per square millimeter. The Intel part has no listed transistor count or die size, as it is integrated into the CPU package.

The memory subsystem is one of the largest architectural divides. The Intel P630 uses system shared memory, meaning it borrows from the host system’s RAM. Its memory type, bus width, and bandwidth are all listed as system dependent. The GTX 970M has 6 GB of dedicated GDDR5 memory on a 192-bit bus, delivering 120.3 GB/s of bandwidth. The memory clock runs at 1253 MHz, which translates to 5 Gbps effective. This dedicated memory is critical for gaming, where the GPU needs consistent high-speed access to textures and frame buffers.

Clock speeds also differ substantially. The Intel P630 has a base clock of 350 MHz and a boost clock of 1200 MHz. The GTX 970M starts at 924 MHz base and boosts to 1038 MHz. While the Intel part boosts higher relative to its base, the NVIDIA chip runs at nearly triple the base frequency. The GTX 970M’s pixel rate is 49.82 GPixel/s, compared to the Intel part’s 3.600 GPixel/s. Texture rate is 83.04 GTexel/s versus 28.80 GTexel/s. Floating point performance, measured in FP32, is 2.657 TFLOPS for the GTX 970M and 460.8 GFLOPS for the Intel P630.

The Intel part does support FP16 with a 2:1 ratio, delivering 921.6 GFLOPS, a feature the GTX 970M lacks entirely. But for most workloads, FP32 performance matters more, and the NVIDIA card is roughly 5.8 times faster there. The Intel P630 has a TDP of just 15 W, while the GTX 970M has no listed TDP in the database. The GTX 970M uses an MXM module form factor with no power connectors, and its bus interface is MXM-B (3.0). The Intel part uses a Ring Bus interface and is an IGP, meaning it has no slot width or power connectors.

Specification Differences

Both GPUs share some API support. They both support DirectX 12 (12_1) and OpenGL 4.6. The GTX 970M additionally supports Vulkan 1.4, while the Intel P630 is limited to Vulkan 1.3. The display outputs differ: the Intel part is motherboard dependent, while the GTX 970M is portable device dependent. The production status for both is end-of-life.

The release dates are separated by nearly six years. The GTX 970M was released on October 6, 2014. The Intel UHD Graphics P630 arrived on May 12, 2020. The GTX 970M has a predecessor, the GeForce 800M, and a successor, the GeForce 10 Mobile. The Intel part has no listed predecessor or successor.

The shading unit count is the most striking difference. The GTX 970M has 1280 shading units, the Intel P630 has 192, a ratio of about 6.7 to 1. TMUs are 80 versus 24, and ROPs are 48 versus 3. The ROP count is particularly lopsided and directly affects fill-rate limited scenarios such as high-resolution rendering with heavy overdraw. The GTX 970M’s 49.82 GPixel/s pixel rate is more than 13 times the Intel part’s 3.600 GPixel/s.

The Intel P630 has a 15 W TDP, making it suitable for ultraportable and low-power designs. The GTX 970M, as an MXM module, is designed for larger gaming laptops where cooling and power delivery are more robust. The Intel part’s memory bandwidth is system dependent, meaning its performance can vary widely depending on the laptop’s RAM configuration. The GTX 970M’s 120.3 GB/s is fixed and independent of the host system.

FAQ

Q: Which GPU is faster in the Geekbench OpenCL test?

A: The NVIDIA GeForce GTX 970M scores 18,946 points in Geekbench OpenCL, while the Intel UHD Graphics P630 scores 5,111 points. The NVIDIA card is 73% faster in this test.

Q: Does the Intel UHD Graphics P630 beat the GTX 970M in any benchmark?

A: No. In the recorded head-to-head benchmarks, the GTX 970M wins both the Geekbench OpenCL and Geekbench Vulkan tests. The Intel part has zero recorded wins against the GTX 970M.

Q: How does the Intel UHD Graphics P630 compare to its nearest rivals?

A: The Intel part averages 5,370 points. It is 0.2% ahead of the AMD Radeon R7 M445, 0.9% ahead of the NVIDIA GeForce 840M, and 1% ahead of the NVIDIA GeForce 930A. The AMD Radeon R7 M365X is 0.8% ahead of it.

Q: What is the memory configuration of the GTX 970M?

A: The GTX 970M has 6 GB of GDDR5 memory on a 192-bit bus, with a bandwidth of 120.3 GB/s. Its memory clock is 1253 MHz, which is 5 Gbps effective.

Q: What API versions do the two GPUs support?

A: Both support DirectX 12 (12_1) and OpenGL 4.6. The GTX 970M supports Vulkan 1.4, while the Intel UHD Graphics P630 supports Vulkan 1.3.

Q: What is the process node for each GPU?

A: The Intel UHD Graphics P630 uses a 14 nm+++ process at Intel. The NVIDIA GeForce GTX 970M uses a 28 nm process at TSMC.

The Verdict

The data points to a straightforward conclusion. If you need a GPU for gaming, 3D rendering, or any compute-heavy task, the NVIDIA GeForce GTX 970M is the only viable choice between these two. Its 73% and 69.2% leads in the head-to-head tests are not close calls. The 1280 shading units, 48 ROPs, and dedicated 6 GB GDDR5 memory with 120.3 GB/s bandwidth put it in an entirely different performance tier. The Intel UHD Graphics P630 cannot sustain playable frame rates in modern titles or handle GPU-accelerated workloads with any reasonable efficiency.

The Intel part is not without merit, but its strengths lie elsewhere. Its 15 W TDP makes it ideal for thin-and-light laptops where battery life and thermals matter more than raw performance. It is competitive with old entry-level discrete GPUs like the GeForce 840M and Radeon R7 M445, which means it is perfectly adequate for office work, web browsing, and video playback. The system shared memory keeps costs down and simplifies the laptop design.

For a buyer choosing between these two, the decision comes down to the intended use case. A user who primarily browses the web, edits documents, and streams video does not need a GTX 970M. The Intel P630 will handle those tasks quietly and efficiently. A user who wants to play games, edit video, or run GPU-accelerated applications should pick the GTX 970M without hesitation. The benchmark results are unambiguous: the GTX 970M is the faster GPU, and the P630 is the more power-efficient one. Both are end-of-life products, but their performance profiles remain relevant for understanding what they can and cannot do.