Intel HD Graphics 630 vs NVIDIA GeForce GTX 460M Comparison

Head-to-Head Benchmarks

The only directly comparable benchmark between the two is Geekbench OpenCL, and the results are decisive. The NVIDIA GeForce GTX 460M scores 4282, while the Intel HD Graphics 630 scores 3587. That gives the GTX 460M a 19.4% advantage, a substantial margin that places these two parts in different performance tiers despite their similar specification sheets elsewhere. The delta is large enough to be immediately noticeable in any compute workload that scales with raw shader output.

Looking at the broader benchmark picture, the GTX 460M’s single OpenCL result of 4282 puts it at the 25th percentile of all GPUs. The Intel part’s average benchmark score across its three tests is 4075, placing it at the 24th percentile. These percentile rankings are nearly identical, which might suggest parity, but the head-to-head OpenCL data tells a different story. The GTX 460M’s nearest rivals include the AMD FirePro W2100 at 4295 (a 0.3% gap) and the AMD Radeon Vega 3 at 4268 (a 0.3% gap), meaning it sits in a tight cluster of low-end discrete parts. The Intel HD Graphics 630’s nearest rivals include the AMD Radeon RX 9060 XT 8 GB at 4093 (a 0.4% gap) and the NVIDIA Quadro K2100M at 4151 (a 1.8% gap), showing it competes in a similar absolute score range but loses the specific OpenCL comparison by a wide margin.

The wins tally is straightforward: the GTX 460M takes 1 win in the head-to-head benchmarks, while the Intel HD Graphics 630 takes 0. There is no benchmark where the Intel part beats the NVIDIA part directly. However, the Intel GPU has additional benchmark entries that the NVIDIA part lacks—Geekbench Metal at 5099 and Geekbench Vulkan at 3540—which are not directly comparable because the GTX 460M has no corresponding scores in those APIs. The OpenCL result remains the only apples-to-apples data point, and it favors the older discrete GPU by nearly a fifth.

Where Each One Wins

The GTX 460M wins in raw OpenCL compute performance. Its 518.4 GFLOPS of FP32 throughput, combined with a 60.00 GB/s memory bandwidth, gives it a clear edge in any workload that stresses shader math or memory transfer. The 19.4% OpenCL delta over the Intel part is consistent with its higher pixel rate (5.400 GPixel/s vs 3.000 GPixel/s) and higher memory bandwidth, even though the Intel part has a higher texture rate (24.00 GTexel/s vs 21.60 GTexel/s). For applications that rely on OpenCL acceleration—video encoding, physics simulation, or GPU compute in older software—the GTX 460M is the stronger choice.

The Intel HD Graphics 630 wins in API support and modern feature coverage. It supports DirectX 12 (12_1), whereas the GTX 460M only supports DirectX 12 (11_0). The Intel part also supports Vulkan 1.3, while the NVIDIA part has no Vulkan support listed. This means the Intel GPU can run newer games and applications that require Vulkan or higher-tier DirectX 12 features, even if its raw compute performance is lower. The Intel part also has FP16 support at 768.0 GFLOPS (2:1), which the GTX 460M lacks entirely, making it more suitable for workloads that leverage half-precision arithmetic. The Intel GPU’s System Shared memory architecture also means it can draw on the full system RAM pool, though bandwidth is System Dependent, so real-world memory performance varies.

In terms of power efficiency, the Intel part is the clear winner. Its 15 W TDP is one-third of the GTX 460M’s 50 W TDP. This is not a performance win, but it is a significant operational advantage, particularly in thin-and-light laptops or systems without discrete graphics cooling. The GTX 460M requires an MXM Module slot and has no power connectors listed, while the Intel part is an IGP with a Ring Bus interface, meaning it is integrated directly into the CPU package.

Architecture Differences

The two GPUs come from different manufacturers, different process nodes, and different architectural generations. The NVIDIA GeForce GTX 460M uses the GF106 chip, built on the Fermi architecture at TSMC’s 40 nm process. The die measures 238 mm² and contains 1,170 million transistors, yielding a transistor density of 4.9M / mm². The Intel HD Graphics 630 uses the Kaby Lake GT2 chip, built on the Generation 9.5 architecture at Intel’s 14 nm++ process. Intel does not list transistor count or die size for this part, but the 14 nm++ node is considerably more advanced than 40 nm, which explains the vast difference in power consumption.

The memory subsystems are fundamentally different. The GTX 460M has 1536 MB of dedicated GDDR5 memory on a 192-bit bus, with a fixed 60.00 GB/s bandwidth. The Intel part uses System Shared memory, meaning it has no dedicated VRAM and relies on the system’s main memory, with bandwidth described as System Dependent. This is a structural advantage for the NVIDIA part in dedicated graphics workloads, as it does not compete with the CPU for memory bandwidth.

The shader and texture configurations are similar but not identical. Both have 192 shading units. The GTX 460M has 32 TMUs and 24 ROPs, while the Intel part has 24 TMUs and only 3 ROPs. The ROP count is a major difference—the GTX 460M has eight times the ROPs of the Intel part. This explains the pixel rate difference: 5.400 GPixel/s for NVIDIA vs 3.000 GPixel/s for Intel. Interestingly, the Intel part has a higher texture rate (24.00 GTexel/s vs 21.60 GTexel/s) despite having fewer TMUs, which suggests a higher texture unit clock relative to its base and boost clocks of 350 MHz and 1000 MHz. The GTX 460M has no base or boost clock listed, only a memory clock of 625 MHz (2.5 Gbps effective).

The feature sets diverge on API support. The GTX 460M supports DirectX 12 (11_0) and OpenGL 4.6, but no Vulkan. The Intel part supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3. The Intel part also has FP16 throughput at 768.0 GFLOPS (2:1), while the GTX 460M has no FP16 capability listed. The NVIDIA part’s FP32 output is 518.4 GFLOPS, compared to Intel’s 384.0 GFLOPS, a 35% advantage for NVIDIA in single-precision compute.

The release dates are separated by six years: the GTX 460M launched on September 2, 2010, and the Intel HD Graphics 630 launched on August 29, 2016. The GTX 460M is part of the GeForce 400M generation, with a predecessor in GeForce 300M and a successor in GeForce 500M. The Intel part is in the HD Graphics (Kaby Lake) generation, with no listed predecessor or successor. Both are end-of-life production status.

The Verdict

From the data, the NVIDIA GeForce GTX 460M is the stronger compute performer. Its OpenCL score of 4282 beats the Intel HD Graphics 630’s 3587 by 19.4%, and its FP32 output of 518.4 GFLOPS is 35% higher. Its dedicated 1536 MB GDDR5 memory with 60.00 GB/s bandwidth provides consistent, predictable memory performance, unlike the Intel part’s System Shared configuration. The GTX 460M also has a significantly higher pixel rate (5.400 GPixel/s vs 3.000 GPixel/s) thanks to its 24 ROPs versus Intel’s 3, making it better suited for fill-rate-bound tasks like legacy rasterization or high-resolution composition.

The Intel HD Graphics 630 is the better choice for modern software compatibility. Its Vulkan 1.3 support and DirectX 12 (12_1) feature level are ahead of the GTX 460M’s DirectX 12 (11_0) and no-Vulkan configuration. It also has FP16 capability, which the NVIDIA part lacks. For users running contemporary games or applications that mandate Vulkan, the Intel part is the only viable option despite its lower raw performance. Its 15 W TDP also makes it far more practical for compact systems where the GTX 460M’s 50 W TDP would be prohibitive.

The decision comes down to workload. For OpenCL compute or legacy DirectX 11-era gaming, the GTX 460M is clearly superior, with a 19.4% benchmark lead and dedicated VRAM. For modern API support, Vulkan-based titles, or power-constrained environments, the Intel HD Graphics 630 is the only sensible pick. The GTX 460M’s 25th percentile ranking versus the Intel part’s 24th percentile is nearly identical, but the head-to-head data shows the NVIDIA part is meaningfully faster in the one metric where they can be compared directly.

FAQ

Q: Which GPU has a higher OpenCL benchmark score?

A: The NVIDIA GeForce GTX 460M scores 4282 in Geekbench OpenCL, while the Intel HD Graphics 630 scores 3587, giving the NVIDIA part a 19.4% lead.

Q: Does the Intel HD Graphics 630 support Vulkan?

A: Yes, the Intel HD Graphics 630 supports Vulkan 1.3. The NVIDIA GeForce GTX 460M has no Vulkan support listed.

Q: What is the power consumption difference?

A: The Intel HD Graphics 630 has a 15 W TDP, while the NVIDIA GeForce GTX 460M has a 50 W TDP, making the Intel part three times more power-efficient.

Q: How much memory does each GPU have?

A: The NVIDIA GeForce GTX 460M has 1536 MB of dedicated GDDR5 memory on a 192-bit bus with 60.00 GB/s bandwidth. The Intel HD Graphics 630 uses System Shared memory with System Dependent bandwidth.

Q: Which GPU has more ROPs?

A: The NVIDIA GeForce GTX 460M has 24 ROPs, while the Intel HD Graphics 630 has only 3 ROPs, resulting in a pixel rate of 5.400 GPixel/s for NVIDIA versus 3.000 GPixel/s for Intel.

Q: Do both GPUs have the same number of shading units?

A: Yes, both the NVIDIA GeForce GTX 460M and the Intel HD Graphics 630 have 192 shading units.

Specification Differences

| Specification | NVIDIA GeForce GTX 460M | Intel HD Graphics 630 |

|---|---|---|

| Chip | GF106 | Kaby Lake GT2 |

| Architecture | Fermi | Generation 9.5 |

| Process Node | 40 nm | 14 nm++ |

| Foundry | TSMC | Intel |

| Transistors | 1,170 million | Not listed |

| Die Size | 238 mm² | Not listed |

| Transistor Density | 4.9M / mm² | Not listed |

| Base Clock | Not listed | 350 MHz |

| Boost Clock | Not listed | 1000 MHz |

| Memory Clock | 625 MHz (2.5 Gbps effective) | System Shared |

| Memory Size | 1536 MB | System Shared |

| Memory Type | GDDR5 | System Shared |

| Memory Bus Width | 192 bit | System Shared |

| Memory Bandwidth | 60.00 GB/s | System Dependent |

| TMUs | 32 | 24 |

| ROPs | 24 | 3 |

| Pixel Rate | 5.400 GPixel/s | 3.000 GPixel/s |

| Texture Rate | 21.60 GTexel/s | 24.00 GTexel/s |

| FP32 | 518.4 GFLOPS | 384.0 GFLOPS |

| FP16 | Not listed | 768.0 GFLOPS (2:1) |

| TDP | 50 W | 15 W |

| Slot Width | MXM Module | IGP |

| Power Connectors | None | Not listed |

| Bus Interface | PCIe 2.0 x16 | Ring Bus |

| Display Outputs | Portable Device Dependent | Motherboard Dependent |

| DirectX | 12 (11_0) | 12 (12_1) |

| OpenGL | 4.6 | 4.6 |

| Vulkan | Not listed | 1.3 |

| Release Date | 2010-09-02 | 2016-08-29 |

| Production Status | End-of-life | End-of-life |

| Generation | GeForce 400M | HD Graphics (Kaby Lake) |

| Predecessor | GeForce 300M | Not listed |

| Successor | GeForce 500M | Not listed |