NVIDIA GeForce GTX 460M vs NVIDIA GeForce GTX 650 Comparison

FAQ

Q: How do the GeForce GTX 460M and GeForce GTX 650 compare in the recorded OpenCL benchmark?

A: The GeForce GTX 650 scores 4545, while the GeForce GTX 460M scores 4282. The GTX 650 wins this benchmark by 5.8%.

Q: Which GPU has the higher percentile ranking among all GPUs in the database?

A: The GeForce GTX 460M ranks at the 25th percentile, while the GeForce GTX 650 ranks at the 22nd percentile. Despite the GTX 650 winning the head-to-head OpenCL test, the GTX 460M has a slightly higher overall percentile standing.

Q: What are the closest rivals to the GeForce GTX 460M based on average benchmark scores?

A: The nearest rivals include the AMD FirePro W2100 (average score 4295, 0.3 percent slower), the AMD Radeon Vega 3 (average score 4268, 0.3 percent faster), the NVIDIA Quadro K3000M (average score 4241, 1 percent faster), and the NVIDIA GeForce RTX 4070 GDDR6 (average score 4335, 1.2 percent slower).

Q: What are the closest rivals to the GeForce GTX 650 based on average benchmark scores?

A: The nearest rivals include the NVIDIA GeForce MX110 (average score 3834, 0.3 percent slower), the Intel UHD Graphics 710 (average score 3792, 0.8 percent faster), the AMD Radeon R5 Graphics (average score 3883, 1.5 percent slower), and the NVIDIA Quadro 2000 (average score 3898, 1.9 percent slower).

Q: Does the GeForce GTX 650 support any modern APIs that the GeForce GTX 460M does not?

A: Yes. The GeForce GTX 650 supports Vulkan 1.2.175, while the GeForce GTX 460M does not list a Vulkan version. Both GPUs support DirectX 12 (11_0) and OpenGL 4.6.

Q: What are the memory sizes and bandwidths of these two GPUs?

A: The GeForce GTX 460M has 1536 MB of GDDR5 memory on a 192-bit bus with 60.00 GB/s bandwidth. The GeForce GTX 650 has 1024 MB of GDDR5 memory on a 128-bit bus with 80.00 GB/s bandwidth.

Architecture Differences

The two GPUs come from different NVIDIA architectures. The GeForce GTX 460M uses the Fermi architecture with the GF106 chip, fabricated on a 40 nm process at TSMC. The GeForce GTX 650 uses the Kepler architecture with the GK106 chip, fabricated on a 28 nm process, also at TSMC. This process shrink is substantial: the GTX 650 packs 2,540 million transistors into a 221 mm² die, while the GTX 460M has 1,170 million transistors on a larger 238 mm² die. The transistor density tells the story: the GTX 650 reaches 11.5 million transistors per square millimeter, while the GTX 460M manages only 4.9 million. This is a clear generational leap in manufacturing efficiency.

The shading unit count differs sharply. The GTX 460M has 192 shading units, while the GTX 650 has 384, exactly double. Texture mapping units are equal at 32 each, but render output units differ: the GTX 460M has 24 ROPs, the GTX 650 has 16. This means the GTX 460M has a higher ROP-to-shader ratio, which can matter for pixel-bound workloads. The GTX 650 compensates with higher raw throughput in other areas.

Clock speeds for the GPU cores are not listed, but memory clocks are. The GTX 460M runs memory at 625 MHz with 2.5 Gbps effective, while the GTX 650 runs at 1250 MHz with 5 Gbps effective. This doubles the effective memory clock for the GTX 650, but the GTX 460M has a wider 192-bit bus. The GTX 650 ends up with more bandwidth (80.00 GB/s) than the GTX 460M (60.00 GB/s), despite the narrower 128-bit bus.

The GTX 460M is a mobile part, using an MXM Module slot width with no power connectors. The GTX 650 is a desktop single-slot card, requiring one 6-pin connector and a suggested power supply of 250 W. The GTX 650 also supports PCIe 3.0 x16, while the GTX 460M uses PCIe 2.0 x16. Display outputs show a major difference: the GTX 650 offers 1x DVI and 2x DisplayPort 1.2, while the GTX 460M depends on the portable device for output, listed as "Portable Device Dependent."

Head-to-Head Benchmarks

The only direct head-to-head benchmark recorded is the Geekbench OpenCL test. The GeForce GTX 650 scores 4545, and the GeForce GTX 460M scores 4282. The delta is 5.8 percent in favor of the GTX 650. This is a meaningful but not overwhelming margin. In the context of the nearest rivals, a 5.8 percent gap is similar to the spread among the GTX 460M's own rivals, which range from 1.2 percent slower (RTX 4070 GDDR6) to 1 percent faster (Quadro K3000M). For the GTX 650, its rivals cluster within 1.9 percent, so the 5.8 percent difference between these two GPUs is larger than typical neighbor gaps.

The GTX 650 also has additional benchmark entries in the database: a Geekbench Metal score of 2400 and a Geekbench Vulkan score of 4524. The GTX 460M has no recorded Metal or Vulkan scores. This is consistent with its lack of Vulkan support in the API list. The Metal score of 2400 is notably lower than both OpenCL and Vulkan scores for the GTX 650, which could indicate that Metal is not a primary workload for this card, or that the test conditions differ.

The average benchmark score must be interpreted carefully. The GTX 460M has a single benchmark score (4282) and an average benchmark score of 4282. The GTX 650 has three benchmark scores, and its average benchmark score is 3823. This average pulls in the lower Metal and Vulkan scores, so it does not represent the OpenCL head-to-head result. When comparing average scores, the GTX 460M appears higher, but when comparing the only common test (OpenCL), the GTX 650 wins.

The wins count is clear: the GTX 650 wins 1 head-to-head benchmark, while the GTX 460M wins none. That is the recorded data, and it is the only direct comparison available.

The Verdict

Based strictly on the recorded data, the GeForce GTX 650 is the stronger performer in the only benchmark where both are measured. The OpenCL score of 4545 against 4282 is a 5.8 percent advantage. If a workload depends on OpenCL, the GTX 650 is the better pick.

But the GTX 460M has its own arguments. Its percentile ranking is higher (25th vs 22nd), meaning it sits above a larger share of all GPUs in the database. Its average benchmark score is higher (4282 vs 3823), but this is a less reliable measure because the GTX 460M has only one benchmark entry, while the GTX 650 has three, and two of those are on different APIs.

The architecture data suggests the GTX 650 is the more advanced part: a smaller process, twice the shading units, higher memory clock, and faster pixel and texture rates (8.464 GPixel/s vs 5.400 GPixel/s, and 33.86 GTexel/s vs 21.60 GTexel/s). The GTX 460M counters with more ROPs (24 vs 16) and more memory capacity (1536 MB vs 1024 MB), which could help in texture-heavy and high-resolution scenarios where memory size matters.

For most users, the GTX 650 is the recommended choice. It wins the direct benchmark, and its architectural advantages point to better compute and pixel throughput. The GTX 460M is a mobile part, so it is only relevant in laptops, while the GTX 650 is a desktop card. That alone decides the platform. The GTX 460M is end-of-life and has been succeeded by the GeForce 500M series, while the GTX 650 is similarly end-of-life with the GeForce 700 series as its successor.

Specification Differences

The two GPUs differ in every major spec field except a few. Process node: 40 nm for the GTX 460M, 28 nm for the GTX 650. Transistors: 1,170 million vs 2,540 million. Die size: 238 mm² vs 221 mm². Transistor density: 4.9M/mm² vs 11.5M/mm².

Memory: 1536 MB vs 1024 MB. Bus width: 192-bit vs 128-bit. Bandwidth: 60.00 GB/s vs 80.00 GB/s. Memory clock: 625 MHz (2.5 Gbps effective) vs 1250 MHz (5 Gbps effective).

Shading units: 192 vs 384. ROPs: 24 vs 16. Pixel rate: 5.400 GPixel/s vs 8.464 GPixel/s. Texture rate: 21.60 GTexel/s vs 33.86 GTexel/s. FP32: 518.4 GFLOPS vs 812.5 GFLOPS. TMUs are the same at 32.

TDP: 50 W vs 65 W. Slot width: MXM Module vs Single-slot. Power connectors: None vs 1x 6-pin. Suggested PSU: not listed vs 250 W. Bus interface: PCIe 2.0 x16 vs PCIe 3.0 x16. Display outputs: Portable Device Dependent vs 1x DVI and 2x DisplayPort 1.2.

APIs: both have DirectX 12 (11_0) and OpenGL 4.6. The GTX 650 has Vulkan 1.2.175, the GTX 460M has no Vulkan. Dimensions: the GTX 650 is 147 mm (5.8 inches) long, the GTX 460M has no listed length. Release dates: the GTX 460M launched on 2010-09-02, the GTX 650 on 2013-11-26. Predecessor and successor differ: GTX 460M comes from GeForce 300M and leads to GeForce 500M; GTX 650 comes from GeForce 500 and leads to GeForce 700.

Where Each One Wins

The GeForce GTX 650 wins in raw compute throughput. Its FP32 rate is 812.5 GFLOPS versus 518.4 GFLOPS, a 56 percent advantage. Its pixel rate and texture rate are also significantly higher, at 8.464 GPixel/s and 33.86 GTexel/s versus 5.400 GPixel/s and 30 GTexel/s respectively. Any workload that is fill-rate bound or compute bound should favor the GTX 650. The Vulkan support is a clear advantage for modern applications. The GTX 650 also wins on bandwidth, delivering 80.00 GB/s versus 60.00 GB/s.

The GeForce GTX 460M wins on memory capacity with 1536 MB versus 1024 MB. That extra capacity can help in texture-heavy games or applications that exceed the 1 GB limit. It also has more ROPs (24 vs 16), which can improve rasterization in certain pixel-heavy scenes, though the GTX 650's higher pixel rate suggests it still comes out ahead overall. The GTX 460M has a lower TDP (50 W vs 65 W), which is important for mobile platforms where power and heat are limited. Its MXM module form factor is the only option for laptops, so it is the only choice for that segment.

The GTX 650 wins the only direct benchmark, so it is the better desktop performer in the measured OpenCL test. The GTX 460M is the better choice for a laptop that needs a dedicated GPU with lower power draw, but it is a legacy part. The GTX 650 is the better all-around desktop GPU, with higher throughput, better bandwidth, and Vulkan support. The data is clear: for OpenCL workloads, the GTX 650 is 5.8 percent faster. For specialized mobile use, the GTX 460M is the only one with a mobile form factor.