GPU Comparison

The GeForce 945M and GeForce GTX 460 are both end-of-life NVIDIA parts, but they represent completely different eras and design philosophies. The data shows a single benchmark comparison, with the 945M edging out the GTX 460 by a slim 2.2% margin in Geekbench OpenCL. This near-parity in overall score masks significant architectural shifts; the 945M is a low-power mobile chip from 2015, while the GTX 460 is a power-hungry desktop card from 2010. Your choice hinges on platform and power constraints rather than raw performance dominance.

The Verdict

Pick the GeForce 945M if you are constrained to a portable or MXM-based system. It delivers the higher benchmark score (8099 vs 7925) while consuming less than half the power (75 W vs 160 W). It is the only option here that does not require external power connectors, making it suitable for slim, battery-powered designs. The 945M also offers a more modern feature set, including Vulkan 1.4 support, which the GTX 460 lacks entirely.

Pick the GeForce GTX 460 if you are building or upgrading a legacy desktop with a PCIe 2.0 x16 slot. It offers a wider 192-bit memory bus and significantly higher memory bandwidth (86.40 GB/s vs 28.80 GB/s), which can be advantageous in bandwidth-sensitive workloads. Its dual-slot design and 2x 6-pin power connectors indicate it expects a robust power supply (450 W suggested). The GTX 460 was launched with an MSRP of 199 USD, but do not consider that a reflection of current market value.

For most modern use cases, the 945M is the more practical choice due to its efficiency and API support. However, the GTX 460’s superior memory subsystem means it is not strictly obsolete in every task.

Architecture Differences

The two GPUs are built on different fabrication processes and microarchitectures. The 945M uses the GM107 chip on TSMC’s 28 nm process, belonging to the Maxwell architecture. The GTX 460 uses the GF104 chip on TSMC’s 40 nm process, belonging to the older Fermi architecture.

The transistor counts are similar, 1,870 million for the 945M and 1,950 million for the GTX 460, but the die sizes diverge sharply. The 945M’s die is 148 mm², giving it a transistor density of 12.6M / mm². The GTX 460’s die is 332 mm², with a density of just 5.9M / mm². This reflects the process node advantage of the newer card.

The 945M packs 640 shading units, 40 TMUs, and 16 ROPs. The GTX 460 has 336 shading units, 56 TMUs, and 24 ROPs. The 945M relies on more, smaller cores; the GTX 460 uses fewer, larger cores with more texture and pixel processing hardware.

Memory configurations differ completely. The 945M uses 2 GB of DDR3 on a 128-bit bus. The GTX 460 uses 768 MB of GDDR5 on a 192-bit bus. The memory clock is rated at 900 MHz for both, but the effective data rate differs: 1800 Mbps for the 945M and 3.6 Gbps for the GTX 460. This explains the bandwidth gap.

API support also distinguishes them. Both support DirectX 12 (11_0) and OpenGL 4.6. However, the 945M supports Vulkan 1.4, while the GTX 460 lists no Vulkan support. The GTX 460’s display outputs are fixed as 2x DVI and 1x mini-HDMI 1.3a, while the 945M’s are dependent on the portable device it is installed in.

Where Each One Wins

Based on the head-to-head benchmark, the 945M wins the only direct comparison, scoring 8099 against the GTX 460’s 7925. That is a 2.2% advantage. This suggests the 945M has a slight edge in compute-oriented OpenCL tasks.

The GTX 460 wins on memory bandwidth by a wide margin: 86.40 GB/s versus 28.80 GB/s. This is a 300% advantage. For workloads heavily dependent on memory throughput, such as high-resolution texture streaming or certain compute kernels, the GTX 460 could outperform its newer rival despite the lower raw compute score.

The 945M wins decisively on power efficiency. Its 75 W TDP is less than half of the GTX 460’s 160 W. It also has a higher pixel rate (16.32 GPixel/s vs 9.450 GPixel/s) and a higher FP32 throughput (1,305.6 GFLOPS vs 907.2 GFLOPS). The texture rates are close, with the 945M at 40.80 GTexel/s and the GTX 460 at 37.80 GTexel/s.

In practical terms, the 945M should handle general compute and pixel-heavy tasks better. The GTX 460 may feel faster in scenarios where its memory bus and extra ROPs (24 vs 16) can be utilized, but its lower shading unit count and FP32 performance will limit it in modern shader-heavy applications.

FAQ

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

A: The GeForce 945M scores 8099, which is 2.2% higher than the GeForce GTX 460’s 7925.

Q: Does the GTX 460 support Vulkan?

A: No. The GTX 460 lists no Vulkan support, while the 945M supports Vulkan 1.4.

Q: What is the memory bandwidth difference between the two?

A: The GTX 460 has a bandwidth of 86.40 GB/s, which is significantly higher than the 945M’s 28.80 GB/s.

Q: Which card has a higher power consumption?

A: The GTX 460 has a TDP of 160 W, compared to the 945M’s 75 W. The GTX 460 also requires 2x 6-pin power connectors and a 450 W suggested PSU, while the 945M uses no external power connectors.

Q: How do their shading unit counts compare?

A: The 945M has 640 shading units, while the GTX 460 has 336 shading units.

Q: What is the memory capacity of each card?

A: The 945M has 2 GB of DDR3 memory, while the GTX 460 has 768 MB of GDDR5 memory.

Head-to-Head Benchmarks

The only direct benchmark result is for Geekbench OpenCL. The GeForce 945M wins with a score of 8099 against the GTX 460’s 7925. The delta is 2.2% in favor of the 945M. This is a narrow victory, placing both cards in a similar performance tier.

Looking at the nearest rivals, the 945M’s 8099 score sits between the NVIDIA GRID K2 (8080) and the AMD Radeon R9 M360 (8129). It is 0.2% ahead of the GRID K2 and 0.4% behind the R9 M360. The GTX 460’s 7925 score is 0.2% ahead of the NVIDIA Quadro K4100M (7906) and 1.4% behind the NVIDIA GeForce GTX 880M (8040).

The 945M also beats the GTX 460 in pixel rate (16.32 GPixel/s vs 9.450 GPixel/s) and FP32 compute (1,305.6 GFLOPS vs 907.2 GFLOPS). These are not benchmark scores but theoretical peak rates. The GTX 460’s texture rate (37.80 GTexel/s) is close to but lower than the 945M’s 40.80 GTexel/s.

The GTX 460’s only clear technical win is bandwidth, where its 86.40 GB/s dwarfs the 945M’s 28.80 GB/s. This is a 3x advantage and could be a deciding factor in specific bandwidth-bound applications.

Specification Differences

The following table summarizes only the fields where the two GPUs differ.

| Specification | GeForce 945M | GeForce GTX 460 |

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

| Chip | GM107 | GF104 |

| Architecture | Maxwell | Fermi |

| Generation | GeForce 900M | GeForce 400 |

| Process Node | 28 nm | 40 nm |

| Transistors | 1,870 million | 1,950 million |

| Die Size | 148 mm² | 332 mm² |

| Transistor Density | 12.6M / mm² | 5.9M / mm² |

| Base Clock | 928 MHz | None |

| Boost Clock | 1020 MHz | None |

| Memory Clock | 1800 Mbps effective | 3.6 Gbps effective |

| Memory Size | 2 GB | 768 MB |

| Memory Type | DDR3 | GDDR5 |

| Memory Bus Width | 128 bit | 192 bit |

| Memory Bandwidth | 28.80 GB/s | 86.40 GB/s |

| Shading Units | 640 | 336 |

| TMUs | 40 | 56 |

| ROPs | 16 | 24 |

| Pixel Rate | 16.32 GPixel/s | 9.450 GPixel/s |

| Texture Rate | 40.80 GTexel/s | 37.80 GTexel/s |

| FP32 | 1,305.6 GFLOPS | 907.2 GFLOPS |

| TDP | 75 W | 160 W |

| Slot Width | MXM Module | Dual-slot |

| Power Connectors | None | 2x 6-pin |

| Suggested PSU | None | 450 W |

| Bus Interface | MXM-B (3.0) | PCIe 2.0 x16 |

| Display Outputs | Portable Device Dependent | 2x DVI, 1x mini-HDMI 1.3a |

| Vulkan Support | 1.4 | None |

| Release Date | 2015-10-26 | 2010-07-11 |

| Predecessor | GeForce 800M | GeForce 200 |

| Successor | GeForce 10 Mobile | GeForce 500 |

| Launch MSRP | None | 199 USD |

The 945M is a smaller, denser, more efficient chip. The GTX 460 is a larger, older design with a wider memory path. Both are end-of-life products with no future support roadmap.