NVIDIA GeForce GTX 650 Ti vs NVIDIA GeForce GTX 950M Comparison

NVIDIA GeForce GTX 950M and NVIDIA GeForce GTX 650 Ti are both end-of-life graphics solutions from NVIDIA, but they represent different design philosophies: one is a mobile-oriented chip from the Maxwell generation, the other a desktop card from the Kepler era. The benchmark data shows a split decision, with each card claiming one decisive victory in the head-to-head tests, while their overall average scores land within 1% of each other.

Head-to-Head Benchmarks

The two cards split their head-to-head matchups exactly, with one win apiece. In the Geekbench OpenCL test, the GTX 950M scores 9,745 against the GTX 650 Ti's 7,877, a decisive 23.7% advantage. This is the largest margin in either direction and establishes the mobile chip as the clear leader in compute-oriented workloads. The GTX 950M's OpenCL result also sits notably above its own average benchmark score of 8,135, suggesting this test plays to its architectural strengths.

The Geekbench Vulkan test tells the opposite story. Here the GTX 650 Ti reverses the outcome, scoring 8,229 versus the GTX 950M's 6,525, a 20.7% lead for the desktop card. This result is particularly striking because it is the GTX 650 Ti's better benchmark showing; its OpenCL score of 7,877 is below its average of 8,053, while the Vulkan result exceeds it. The split suggests the two cards have complementary strengths: the GTX 950M excels in OpenCL compute, while the GTX 650 Ti handles Vulkan graphics more efficiently.

Looking at the aggregate data, the GTX 950M posts an average benchmark score of 8,135, while the GTX 650 Ti averages 8,053. The difference is a mere 82 points, or roughly 1%. Both cards sit at the 42nd percentile among all GPUs, placing them in identical overall performance tiers. The nearest rival data reinforces this parity: the GTX 950M's closest competitor is the AMD Radeon R9 M360 at 8,129, just 0.1% behind, while the GTX 650 Ti's nearest rival is the NVIDIA GRID K2 at 8,080, which the desktop card trails by 0.3%.

FAQ

Q: Which card wins in OpenCL performance?

A: The NVIDIA GeForce GTX 950M wins the Geekbench OpenCL test decisively, scoring 9,745 compared to the GTX 650 Ti's 7,877, a 23.7% advantage.

Q: Which card wins in Vulkan performance?

A: The NVIDIA GeForce GTX 650 Ti wins the Geekbench Vulkan test, scoring 8,229 against the GTX 950M's 6,525, a 20.7% margin in its favor.

Q: How do their overall average benchmark scores compare?

A: The GTX 950M averages 8,135 across benchmarks, while the GTX 650 Ti averages 8,053. This places them within 1% of each other, and both sit at the 42nd percentile among all GPUs.

Q: What is the memory configuration difference?

A: The GTX 950M uses 4 GB of DDR3 memory on a 128-bit bus, yielding 28.80 GB/s of bandwidth. The GTX 650 Ti uses 1024 MB of GDDR5 on the same 128-bit bus, but delivers 86.40 GB/s of bandwidth, three times the throughput.

Q: Which card has higher power requirements?

A: The GTX 650 Ti has a TDP of 110 W, requires a 1x 6-pin power connector, and suggests a 300 W PSU. The GTX 950M has a 75 W TDP, uses no power connectors, and is an integrated graphics processor (IGP) form factor.

Q: What are the API support differences?

A: Both cards support DirectX 12 (11_0) and OpenGL 4.6. The GTX 950M supports Vulkan 1.4, while the GTX 650 Ti supports the older Vulkan 1.2.175.

Architecture Differences

The two cards come from different NVIDIA architectures and generations. The GTX 950M uses the GM107 chip on the Maxwell architecture, part of the GeForce 900M generation. The GTX 650 Ti uses the GK106S chip on the Kepler architecture, from the GeForce 600 generation. Both are fabricated by TSMC on the same 28 nm process node, but the chip designs diverge significantly from there.

The GTX 650 Ti packs more hardware resources: 2,540 million transistors on a 221 mm² die, versus the GTX 950M's 1,870 million transistors on a 148 mm² die. The larger chip gives the GTX 650 Ti more shading units (768 versus 640) and more texture mapping units (64 versus 40), but both cards have identical 16 render output units. The transistor density is slightly higher on the GTX 950M at 12.6M per mm², compared to 11.5M per mm² on the GTX 650 Ti, reflecting the newer Maxwell design's efficiency.

Clock behavior also differs. The GTX 950M has explicit base and boost clocks of 993 MHz and 1,124 MHz respectively, while the GTX 650 Ti has no base or boost clock listed. Memory clocks show a similar contrast: the GTX 950M runs at 900 MHz (1,800 Mbps effective), while the GTX 650 Ti runs at 1,350 MHz (5.4 Gbps effective). The memory type difference is fundamental — DDR3 on the GTX 950M versus GDDR5 on the GTX 650 Ti — which explains the bandwidth gap.

The GTX 950M is an IGP (integrated graphics processor) with no power connectors and a 75 W TDP, designed for portable devices with display outputs described as "Portable Device Dependent." The GTX 650 Ti is a single-slot desktop card measuring 145 mm (5.7 inches) in length, with 2x DVI and 1x mini-HDMI 1.4a outputs, requiring a 6-pin power connector and a 300 W PSU. The bus interface also differs: the GTX 950M uses PCIe 3.0 x8, while the GTX 650 Ti uses the full PCIe 3.0 x16.

The Verdict

The data presents a genuine trade-off rather than a clear winner. The GTX 950M leads in OpenCL compute by a wide 23.7% margin, while the GTX 650 Ti counters with a 20.7% lead in Vulkan. Their average benchmark scores are nearly identical, separated by less than 1%, and both occupy the 42nd percentile of all GPUs. Neither card can claim overall superiority.

For compute-heavy workloads that leverage OpenCL, the GTX 950M is the stronger choice. Its 9,745 OpenCL score is 21% above its own average and 23.7% above the GTX 650 Ti's corresponding result. The GTX 950M also offers four times the memory capacity (4 GB versus 1024 MB), which matters for larger datasets even if the DDR3 bandwidth is lower.

For Vulkan-based applications and games, the GTX 650 Ti is the better performer. Its 8,229 Vulkan score exceeds the GTX 950M's 6,525 by 20.7%, and it provides substantially higher memory bandwidth at 86.40 GB/s versus 28.80 GB/s. The GTX 650 Ti also has more shading units and TMUs, which can benefit certain rendering workloads.

The GTX 950M is the more power-efficient and compact option, with a 75 W TDP and no power connector requirement, making it suitable for portable systems. The GTX 650 Ti demands 110 W, a 6-pin connector, and a 300 W PSU, but offers a desktop-format card with standard display outputs. Users prioritizing compute performance and memory capacity should favor the GTX 950M; those prioritizing Vulkan graphics and memory bandwidth should favor the GTX 650 Ti.

Specification Differences

The two cards differ across nearly every major specification category. The GTX 950M uses the GM107 chip on Maxwell architecture from the GeForce 900M generation, while the GTX 650 Ti uses the GK106S chip on Kepler from the GeForce 600 generation. The GTX 650 Ti has a larger die (221 mm² versus 148 mm²) and more transistors (2,540 million versus 1,870 million), but lower transistor density (11.5M/mm² versus 12.6M/mm²).

Clock specifications show the GTX 950M with base and boost clocks of 993 MHz and 1,124 MHz, while the GTX 650 Ti lists no base or boost clocks. Memory clocks differ significantly: the GTX 950M runs at 900 MHz (1,800 Mbps effective), while the GTX 650 Ti runs at 1,350 MHz (5.4 Gbps effective). Memory capacity favors the GTX 950M at 4 GB DDR3, versus the GTX 650 Ti's 1024 MB GDDR5, but bandwidth heavily favors the GTX 650 Ti at 86.40 GB/s versus 28.80 GB/s.

Compute resources differ: the GTX 650 Ti has 768 shading units and 64 TMUs, while the GTX 950M has 640 shading units and 40 TMUs; both have 16 ROPs. Pixel rate favors the GTX 950M at 17.98 GPixel/s versus 14.85 GPixel/s, while texture rate favors the GTX 650 Ti at 59.39 GTexel/s versus 44.96 GTexel/s. FP32 performance is nearly identical: 1,438.7 GFLOPS for the GTX 950M and 1,425.4 GFLOPS for the GTX 650 Ti.

Power and form factor diverge sharply: the GTX 950M has a 75 W TDP, is an IGP with no power connectors, and uses PCIe 3.0 x8; the GTX 650 Ti has a 110 W TDP, is a single-slot card with a 6-pin connector, a 300 W PSU suggestion, and uses PCIe 3.0 x16. Display outputs are portable-device-dependent on the GTX 950M, versus 2x DVI and 1x mini-HDMI 1.4a on the GTX 650 Ti. API support is identical for DirectX 12 (11_0) and OpenGL 4.6, but Vulkan support differs: 1.4 on the GTX 950M versus 1.2.175 on the GTX 650 Ti. Release dates are March 2015 for the GTX 950M and October 2012 for the GTX 650 Ti.

Where Each One Wins

The GTX 950M wins in OpenCL compute performance, posting a 23.7% higher score than the GTX 650 Ti. It also wins on memory capacity with 4 GB versus 1024 MB, on pixel rate (17.98 GPixel/s versus 14.85 GPixel/s), and on power efficiency with a 75 W TDP versus 110 W. Its boost clock of 1,124 MHz provides a defined performance ceiling, and its Vulkan 1.4 API support is more modern than the GTX 650 Ti's 1.2.175. The GTX 950M's smaller die (148 mm² versus 221 mm²) and higher transistor density (12.6M/mm² versus 11.5M/mm²) reflect a more compact design.

The GTX 650 Ti wins in Vulkan performance, beating the GTX 950M by 20.7% in that benchmark. It also wins decisively on memory bandwidth at 86.40 GB/s, three times the GTX 950M's 28.80 GB/s, thanks to GDDR5 memory. The GTX 650 Ti has more shading units (768 versus 640), more TMUs (64 versus 40), and a higher texture rate (59.39 GTexel/s versus 44.96 GTexel/s). Its FP32 output is slightly higher at 1,425.4 GFLOPS versus 1,438.7 GFLOPS, though this difference is marginal. The GTX 650 Ti also offers a full PCIe 3.0 x16 interface versus x8, and its desktop form factor includes standard display outputs. It launched with a 149 USD MSRP, a fact stated here for historical context.