NVIDIA GeForce GTX 965M vs NVIDIA GeForce RTX 3050 Ti Mobile Comparison

FAQ

Q: How does the NVIDIA GeForce GTX 965M compare to the RTX 3050 Ti Mobile in raw compute performance?

A: The RTX 3050 Ti Mobile dominates. In Geekbench OpenCL, it scores 57,915 versus the GTX 965M's 14,509, a delta of 74.9% in favor of the newer card. The Vulkan result is similar: 55,812 versus 14,299, a 74.4% advantage.

Q: Which GPU has more shading units and texture mapping units?

A: The RTX 3050 Ti Mobile has 2,560 shading units and 80 TMUs, while the GTX 965M has 1,024 shading units and 64 TMUs. Both cards have 32 ROPs.

Q: What are the memory specifications of each card?

A: The GTX 965M uses 2 GB of GDDR5 on a 128-bit bus with 80.19 GB/s bandwidth. The RTX 3050 Ti Mobile has 4 GB of GDDR6 on the same 128-bit bus but with 192.0 GB/s bandwidth.

Q: Does the RTX 3050 Ti Mobile support hardware ray tracing?

A: Yes, the RTX 3050 Ti Mobile includes 20 RT cores and 80 tensor cores. The GTX 965M has no RT cores or tensor cores, as it is based on the Maxwell 2.0 architecture.

Q: What is the transistor density difference between the two chips?

A: The RTX 3050 Ti Mobile's GA106 chip packs 43.5 million transistors per mm², compared to the GTX 965M's GM204 at 13.1 million per mm². The newer chip is built on an 8 nm Samsung process, while the older one uses TSMC's 28 nm node.

Q: Which card has a higher average benchmark score?

A: The GTX 965M has an average benchmark score of 14,404, while the RTX 3050 Ti Mobile averages 12,940. However, this aggregate is drawn from different test suites, and the direct head-to-head results overwhelmingly favor the RTX card.

Architecture Differences

The GTX 965M is built on the Maxwell 2.0 architecture, using the GM204 chip manufactured by TSMC on a 28 nm process. The RTX 3050 Ti Mobile uses the Ampere architecture with the GA106 chip from Samsung on an 8 nm node. This process shrink allows the GA106 to fit 12,000 million transistors on a 276 mm² die, giving a density of 43.5 million transistors per mm². The GM204, by contrast, contains 5,200 million transistors on a much larger 398 mm² die, with a density of only 13.1 million per mm².

The compute core layout differs substantially. The GTX 965M has 1,024 shading units, 64 TMUs, and 32 ROPs. The RTX 3050 Ti Mobile has 2,560 shading units, 80 TMUs, and also 32 ROPs. Beyond the traditional cores, the Ampere chip adds 20 RT cores for hardware ray tracing and 80 tensor cores for AI workloads, neither of which exist on the Maxwell part.

Memory architecture also separates the two. The GTX 965M uses 2 GB of GDDR5 with a 128-bit bus and 80.19 GB/s bandwidth. The RTX 3050 Ti Mobile ships with 4 GB of GDDR6 on the same 128-bit bus, but bandwidth jumps to 192.0 GB/s. The memory clock is rated at 1253 MHz (5 Gbps effective) for the older card, versus 1500 MHz (12 Gbps effective) for the newer one.

The interface and form factor differ as well. The GTX 965M is an MXM Module with an MXM-B (3.0) bus interface, while the RTX 3050 Ti Mobile is an IGP with a PCIe 4.0 x16 interface. Both are portable-device dependent for display outputs and use no external power connectors.

DirectX support marks a clear generational gap. The GTX 965M supports DirectX 12 (12_1), while the RTX 3050 Ti Mobile supports DirectX 12 Ultimate (12_2). Both cards support OpenGL 4.6 and Vulkan 1.4.

Clock speeds are counterintuitive: the GTX 965M has a higher base clock at 924 MHz and boost at 950 MHz, while the RTX 3050 Ti Mobile starts lower at 735 MHz base but boosts to 1035 MHz. The RTX card also has a 75 W TDP rating, while the GTX card has no listed TDP.

Head-to-Head Benchmarks

The only two shared benchmark results in the database are Geekbench OpenCL and Geekbench Vulkan, and both show a massive swing toward the RTX 3050 Ti Mobile.

In Geekbench OpenCL, the RTX 3050 Ti Mobile scores 57,915 against the GTX 965M's 14,509. That is a 74.9% delta, meaning the newer card is roughly four times faster in this compute workload. The GTX 965M's score of 14,509 places it just above the AMD Radeon RX Vega 11 (14,385, a 0.1% delta) and NVIDIA GeForce GTX TITAN (14,373, a 0.2% delta) in the database's nearest rival list. The RTX 3050 Ti Mobile's 57,915, by contrast, sits far above any of its listed nearest rivals, which include the GTX 1660 SUPER at 12,986 (a -0.4% delta).

In Geekbench Vulkan, the pattern repeats. The RTX 3050 Ti Mobile posts 55,812 versus 14,299 for the GTX 965M, a 74.4% advantage. The older card's Vulkan score of 14,299 keeps it in the same performance tier as its OpenCL result, showing that the Maxwell architecture is limited in both APIs. The RTX card's Vulkan score is slightly lower than its OpenCL score, but still overwhelming.

The RTX 3050 Ti Mobile has additional benchmark entries in the database that the GTX 965M lacks, including PassMark tests and a 3DMark Steel Nomad DX12 result. Its PassMark G3D score is 10,093, with a GPU compute score of 4,305. The DirectX 9 PassMark score is 120, DirectX 10 is 60, DirectX 11 is 76, and DirectX 12 is 49. The 3DMark Steel Nomad DX12 score is 469. These cannot be compared directly to the GTX 965M, but they provide context for where the Ampere part lands across legacy and modern APIs.

The average benchmark score in the database tells a different story at first glance: the GTX 965M averages 14,404 while the RTX 3050 Ti Mobile averages 12,940. This is because the averages are computed over different test sets. The GTX 965M only has the two Geekbench results, while the RTX card's average includes many lower-scoring PassMark tests, dragging its aggregate down. The direct head-to-head data, not the aggregate, is the appropriate measure for comparing these two, and it is decisively in favor of the RTX 3050 Ti Mobile.

Specification Differences

The two GPUs differ across nearly every major specification category. The GTX 965M uses the GM204 chip on a 28 nm TSMC process, while the RTX 3050 Ti Mobile uses the GA106 chip on Samsung's 8 nm node. Transistor count rises from 5,200 million to 12,000 million, and die size shrinks from 398 mm² to 276 mm². Transistor density improves from 13.1 million per mm² to 43.5 million per mm².

Shading units increase from 1,024 to 2,560, and TMUs from 64 to 80. ROPs remain identical at 32. The RTX card adds 20 RT cores and 80 tensor cores; the GTX card has none. Pixel rate improves modestly from 30.40 GPixel/s to 33.12 GPixel/s, while texture rate jumps from 60.80 GTexel/s to 82.80 GTexel/s. FP32 compute rises from 1.946 TFLOPS to 5.299 TFLOPS, and the RTX card also supports FP16 at 5.299 TFLOPS (1:1), which the GTX card does not list.

Memory capacity doubles from 2 GB to 4 GB, and memory type changes from GDDR5 to GDDR6. Bus width stays at 128 bit, but bandwidth increases from 80.19 GB/s to 192.0 GB/s. Memory clocks move from 1253 MHz (5 Gbps effective) to 1500 MHz (12 Gbps effective).

Base clock drops from 924 MHz to 735 MHz, but boost clock rises from 950 MHz to 1035 MHz. TDP is listed only for the RTX card at 75 W. Form factor changes from MXM Module to IGP, and bus interface from MXM-B (3.0) to PCIe 4.0 x16. DirectX support moves from 12 (12_1) to 12 Ultimate (12_2). The GTX 965M was released on 2015-01-08, and the RTX 3050 Ti Mobile on 2021-05-10. The GTX card's predecessor is the GeForce 800M and its successor is GeForce 10 Mobile; the RTX card's predecessor is GeForce 20 Mobile, with no successor listed. Both are end-of-life production status.

The Verdict

The data is unambiguous: the RTX 3050 Ti Mobile is the far stronger GPU. In the only shared benchmarks, it leads by 74.9% in Geekbench OpenCL and 74.4% in Geekbench Vulkan. That is not a marginal improvement; it is a generational leap in compute throughput, driven by a denser 8 nm chip, more than double the shading units, and double the memory bandwidth.

The GTX 965M's only consolation is its higher base clock (924 MHz versus 735 MHz) and its place in the database's aggregate average, which is skewed by the different test sets. In actual shared workloads, it trails badly. Its 14,404 average score places it near the AMD Radeon RX Vega 11 and Intel Iris Xe MAX, not in the same league as the Ampere part.

Buyers or system builders looking at the RTX 3050 Ti Mobile should expect a card that sits close to the GTX 1660 SUPER in the database's nearest rival ranking (12,986 average score, a -0.4% delta), which speaks to its standing as a competent 1080p-class mobile GPU. The GTX 965M, meanwhile, is best understood as an older Maxwell part that remains competitive only against integrated graphics like the Radeon Vega 11.

For modern workloads, the RTX 3050 Ti Mobile is the clear choice: it offers hardware ray tracing, tensor cores, DirectX 12 Ultimate support, and 4 GB of faster GDDR6 memory. The GTX 965M lacks all of these features and cannot match the newer card's raw throughput. The verdict from the recorded data is simple: if the choice is between these two, the RTX 3050 Ti Mobile wins on every meaningful benchmark, and the GTX 965M should only be considered when the older MXM form factor or legacy compatibility is a hard constraint.