NVIDIA GeForce GTX 460 v2 vs NVIDIA GeForce GTX 650 Ti Boost Comparison

# NVIDIA GeForce GTX 460 v2 vs NVIDIA GeForce GTX 650 Ti Boost

The NVIDIA GeForce GTX 460 v2 and the NVIDIA GeForce GTX 650 Ti Boost represent two distinct generations of NVIDIA's mid-range GPU lineup, separated by roughly 18 months of architectural evolution. The GTX 460 v2, built on Fermi 2.0, launched in September 2011 with a launch MSRP of 199 USD, while the GTX 650 Ti Boost arrived in March 2013 with a launch MSRP of 169 USD, built on the Kepler architecture. The benchmark data available shows a single head-to-head comparison in Geekbench OpenCL, where the GTX 650 Ti Boost scores 9,302 against the GTX 460 v2's 8,743, resulting in a 6% advantage for the newer card. However, the full picture requires examining architectural differences, memory configurations, and the broader benchmark context to determine where each card genuinely excels.

Where Each One Wins

The GTX 650 Ti Boost wins the only direct head-to-head benchmark available, the Geekbench OpenCL test, with a score of 9,302 compared to the GTX 460 v2's 8,743 — a 6% margin. This single data point suggests the Kepler card has a measurable edge in compute workloads, likely stemming from its significantly higher shader count and memory bandwidth. The GTX 650 Ti Boost also demonstrates versatility across multiple API benchmarks: it scores 4,858 in Geekbench Metal, 9,302 in Geekbench OpenCL, and 10,041 in Geekbench Vulkan, indicating solid performance across different compute interfaces. The GTX 460 v2, by contrast, only has a single OpenCL benchmark score of 8,743 in the data pack, offering no comparable data for Metal or Vulkan — a notable limitation given that the older card does not list Vulkan support in its API specifications.

The GTX 460 v2's advantage lies not in raw compute scores but in its transistor density profile and legacy positioning. With 1,950 million transistors on a 332 mm² die, it achieves a density of 5.9M transistors per mm², whereas the GTX 650 Ti Boost packs 2,540 million transistors into a smaller 221 mm² die, reaching 11.5M per mm². For workloads that favor the Fermi architecture's particular scheduling characteristics — or for systems constrained by PCIe 2.0 rather than PCIe 3.0 — the GTX 460 v2 may still hold relevance. The percentile rankings are close: the GTX 460 v2 sits at the 44th percentile of all GPUs, while the GTX 650 Ti Boost sits at the 42nd percentile, meaning the older card actually ranks slightly higher globally despite losing the direct comparison.

Architecture Differences

The fundamental architectural divide is between Fermi 2.0 and Kepler. The GTX 460 v2 uses the GF114 chip on a 40 nm TSMC process, while the GTX 650 Ti Boost uses the GK106 chip on a 28 nm TSMC process. This process shrink allows the Kepler card to pack 2,540 million transistors into a 221 mm² die, versus 1,950 million in 332 mm² for Fermi — a dramatic density improvement from 5.9M to 11.5M transistors per mm². The shader configuration differs substantially: the GTX 460 v2 has 336 shading units, 56 texture mapping units, and 24 ROPs, while the GTX 650 Ti Boost has 768 shading units, 64 TMUs, and 24 ROPs. The Kepler card more than doubles the shading units while adding 8 TMUs, yet both cards maintain identical 24 ROPs.

Memory architecture shows both convergence and divergence. Both cards use GDDR5 with a 192-bit bus width, but the GTX 650 Ti Boost doubles the capacity to 2 GB versus 1 GB on the GTX 460 v2. The memory clock also rises from 1002 MHz (4 Gbps effective) on the older card to 1502 MHz (6 Gbps effective) on the newer one, yielding bandwidth of 144.2 GB/s versus 96.19 GB/s — a 50% improvement. Clock speeds differ as well: the GTX 460 v2 lists no base or boost clock in the data, while the GTX 650 Ti Boost runs at 980 MHz base and 1032 MHz boost. The GTX 650 Ti Boost also supports Vulkan 1.2.175, whereas the GTX 460 v2 lists no Vulkan support; both cards support DirectX 12 (11_0) and OpenGL 4.6.

Power and interface specifications reveal further divergence. The GTX 460 v2 draws 160 W TDP and requires 2x 6-pin power connectors with a suggested 450 W PSU, while the GTX 650 Ti Boost draws only 134 W TDP, needs a single 6-pin connector, and suggests a 300 W PSU. The bus interface also advances from PCIe 2.0 x16 on the GTX 460 v2 to PCIe 3.0 x16 on the GTX 650 Ti Boost. Display outputs differ as well: the older card offers 2x DVI and 1x mini-HDMI 1.3a, while the newer card provides 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2.

FAQ

Q: Which card has higher raw compute performance in OpenCL?

A: The GTX 650 Ti Boost scores 9,302 in Geekbench OpenCL, which is 6% higher than the GTX 460 v2's 8,743. This is the only direct head-to-head benchmark available in the data.

Q: Do these cards support the same APIs?

A: Both support DirectX 12 (11_0) and OpenGL 4.6. However, the GTX 650 Ti Boost additionally supports Vulkan 1.2.175, while the GTX 460 v2 lists no Vulkan support. The GTX 650 Ti Boost also has benchmark scores for Metal and Vulkan, which the GTX 460 v2 lacks.

Q: How do their memory configurations compare?

A: The GTX 460 v2 has 1 GB of GDDR5 on a 192-bit bus with 96.19 GB/s bandwidth. The GTX 650 Ti Boost has 2 GB of GDDR5 on the same 192-bit bus but with 144.2 GB/s bandwidth, representing a 50% bandwidth increase and double the capacity.

Q: What are the power requirements for each card?

A: The GTX 460 v2 has a 160 W TDP and requires 2x 6-pin power connectors with a suggested 450 W PSU. The GTX 650 Ti Boost has a 134 W TDP, needs only 1x 6-pin connector, and suggests a 300 W PSU.

Q: How do these cards rank against all GPUs?

A: The GTX 460 v2 sits at the 44th percentile of all GPUs, while the GTX 650 Ti Boost sits at the 42nd percentile. Despite the GTX 650 Ti Boost winning the direct comparison, the GTX 460 v2 ranks slightly higher globally.

Q: What is the transistor and die size difference?

A: The GTX 460 v2 uses 1,950 million transistors on a 332 mm² die (5.9M per mm²), while the GTX 650 Ti Boost uses 2,540 million transistors on a 221 mm² die (11.5M per mm²). The newer card packs 30% more transistors into a 33% smaller die.

Specification Differences

| Specification | GTX 460 v2 | GTX 650 Ti Boost |

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

| Architecture | Fermi 2.0 | Kepler |

| Chip | GF114 | GK106 |

| Process Node | 40 nm | 28 nm |

| Transistors | 1,950 million | 2,540 million |

| Die Size | 332 mm² | 221 mm² |

| Transistor Density | 5.9M / mm² | 11.5M / mm² |

| Base Clock | Not specified | 980 MHz |

| Boost Clock | Not specified | 1032 MHz |

| Memory Clock | 1002 MHz (4 Gbps effective) | 1502 MHz (6 Gbps effective) |

| Memory Size | 1024 MB | 2 GB |

| Memory Bandwidth | 96.19 GB/s | 144.2 GB/s |

| Shading Units | 336 | 768 |

| TMUs | 56 | 64 |

| Pixel Rate | 10.91 GPixel/s | 16.51 GPixel/s |

| Texture Rate | 43.62 GTexel/s | 66.05 GTexel/s |

| FP32 Performance | 1,046.3 GFLOPS | 1.585 TFLOPS |

| TDP | 160 W | 134 W |

| Power Connectors | 2x 6-pin | 1x 6-pin |

| Suggested PSU | 450 W | 300 W |

| Bus Interface | PCIe 2.0 x16 | PCIe 3.0 x16 |

| Display Outputs | 2x DVI, 1x mini-HDMI 1.3a | 2x DVI, 1x HDMI 1.4a, 1x DisplayPort 1.2 |

| Vulkan Support | Not specified | 1.2.175 |

| Release Date | 2011-09-23 | 2013-03-25 |

| Launch MSRP | 199 USD | 169 USD |

Head-to-Head Benchmarks

The sole direct comparison in the data is Geekbench OpenCL, where the GTX 650 Ti Boost scores 9,302 against the GTX 460 v2's 8,743. The delta of 6% in favor of the Kepler card reflects the architectural advancements: the GTX 650 Ti Boost has 768 shading units versus 336, a 2.29x increase, and its FP32 throughput of 1.585 TFLOPS is 51% higher than the GTX 460 v2's 1,046.3 GFLOPS. The memory bandwidth advantage of 144.2 GB/s versus 96.19 GB/s provides a 50% headroom for bandwidth-bound workloads, which likely contributes to the OpenCL score gap.

However, the GTX 460 v2's percentile ranking of 44 versus the GTX 650 Ti Boost's 42 suggests that in the broader GPU landscape, the older card fares slightly better relative to its contemporaries. This could be because the Fermi architecture's 40 nm process, while less dense, may offer different compute characteristics that some workloads favor. The GTX 460 v2's nearest rivals include the NVIDIA GeForce RTX 3050 A Mobile (avg score 8,746, delta 0%), the Quadro P2200 (8,686, delta 0.7%), and AMD cards like the R9 M265X (8,851, delta -1.2%) and Pro WX 5100 (8,863, delta -1.4%). The GTX 650 Ti Boost's nearest rivals include the GRID K2 (8,080, delta -0.2%), the GTX 650 Ti (8,053, delta 0.2%), GTX 880M (8,040, delta 0.3%), and Quadro P5000 (8,039, delta 0.3%).

The GTX 650 Ti Boost also provides additional benchmark coverage with Metal (4,858) and Vulkan (10,041) scores, though these cannot be compared directly to the GTX 460 v2, which lacks corresponding data. The Vulkan score of 10,041 is notably higher than its OpenCL score of 9,302, suggesting the Kepler architecture responds well to modern compute APIs. The GTX 460 v2 has no such data, reflecting its older API support profile.

The Verdict

The data clearly favors the GTX 650 Ti Boost in raw performance terms. It wins the only head-to-head benchmark by 6%, offers double the memory capacity (2 GB versus 1 GB), delivers 50% more bandwidth, and provides higher pixel and texture rates — 16.51 GPixel/s versus 10.91 GPixel/s, and 66.05 GTexel/s versus 43.62 GTexel/s, respectively. Its FP32 performance of 1.585 TFLOPS substantially exceeds the GTX 460 v2's 1,046.3 GFLOPS. The newer card also achieves all this while consuming less power (134 W versus 160 W), requiring fewer power connectors (1x 6-pin versus 2x 6-pin), and suggesting a lower PSU rating (300 W versus 450 W).

For users prioritizing compute performance, modern API support, or memory capacity, the GTX 650 Ti Boost is the clear choice from the data. Its Vulkan support and additional benchmark coverage in Metal and Vulkan indicate broader software compatibility. The GTX 460 v2, however, should not be dismissed entirely — its 44th percentile ranking versus the 42nd for the GTX 650 Ti Boost suggests that in the broader GPU ecosystem, it holds its position comparably. The older card's lower transistor density (5.9M per mm² versus 11.5M per mm²) and larger die (332 mm² versus 221 mm²) reflect a less efficient design, yet its launch MSRP of 199 USD was higher than the GTX 650 Ti Boost's 169 USD, making the newer card both cheaper at launch and more capable in the measured benchmarks.

The verdict hinges on use case. For anyone building a system with a PCIe 3.0 motherboard, requiring 2 GB of VRAM for modern workloads, or wanting Vulkan support, the GTX 650 Ti Boost is the data-supported winner. For those constrained to PCIe 2.0 platforms, seeking a card that ranks slightly higher in the global percentile distribution, or preferring the Fermi architecture's characteristics, the GTX 460 v2 remains a defensible option — though the 6% OpenCL deficit and substantial specification gaps make it the weaker choice in nearly every measurable category.