NVIDIA GeForce GTS 450 vs NVIDIA GeForce GTX 765M Comparison

Head-to-Head Benchmarks

The recorded head-to-head data contains a single benchmark comparison between the NVIDIA GeForce GTX 765M and the NVIDIA GeForce GTS 450: Geekbench OpenCL. This is a decisive result. The GTX 765M scores 7,176 points, while the GTS 450 scores 4,893 points. The delta is 46.7% in favor of the GTX 765M, making it the clear winner in this matchup. With one test compared, the GTX 765M takes one win, and the GTS 450 takes none.

This 46.7% advantage is substantial, not marginal. To put it in context, the GTS 450's average benchmark score is 4,893, which places it in the 28th percentile of all GPUs. The GTX 765M, by contrast, averages 5,501 across its benchmark suite, landing in the 32nd percentile. That percentile gap of four points may sound modest, but the raw score difference tells a different story: the GTX 765M is nearly half again as fast in the one test where both were measured.

Looking at the GTX 765M's nearest rivals reinforces how meaningful its score is. Its average of 5,501 sits within a tight cluster: the NVIDIA GeForce MX130 averages 5,508 (a delta of -0.1%), the AMD FirePro M4000 averages 5,537 (-0.7%), the AMD Radeon R7 M440 averages 5,483 (+0.3%), and the NVIDIA Quadro M4000 averages 5,467 (+0.6%). The GTX 765M is effectively tied with all of these, within a single percentage point. This means its OpenCL result of 7,176 is not an outlier; it is consistent with a GPU that performs at the upper edge of its peer group.

The GTS 450's nearest rivals tell a different story. Its average of 4,893 is bracketed by the NVIDIA GeForce RTX 5060 Ti 8 GB at 4,901 (-0.2%), the AMD FirePro W5130M at 4,904 (-0.2%), the AMD Radeon R6 M255DX at 4,867 (+0.5%), and the AMD Radeon R7 M265 at 4,929 (-0.7%). Notably, the RTX 5060 Ti 8 GB appears in this list, which is a modern card, yet its average score is statistically indistinguishable from the GTS 450's. This suggests the GTS 450, despite its age, holds its own in synthetic OpenCL workloads against much newer hardware, at least in this benchmark database.

However, the head-to-head comparison is unambiguous. When both GPUs run the same OpenCL test, the GTX 765M outperforms the GTS 450 by 2,283 points, or 46.7%. No other benchmark was recorded for both cards, so this single metric stands as the only direct measurement. The verdict from the data is clear: the GTX 765M is the faster GPU.

The Verdict

The data points to one conclusion: the NVIDIA GeForce GTX 765M is the superior choice for raw compute performance. Its OpenCL score of 7,176 crushes the GTS 450's 4,893 by 46.7%, and its average benchmark score of 5,501 exceeds the GTS 450's 4,893 by 12.4%. The percentile rankings agree: 32nd for the GTX 765M versus 28th for the GTS 450.

Who should pick the GTX 765M? Anyone prioritizing compute throughput, OpenCL workloads, or general GPU acceleration. It also offers more memory, 2 GB versus 1 GB, which matters for larger datasets or higher-resolution textures. The GTX 765M is a mobile part (MXM Module), so it is suited for laptops or modular systems where power draw is a concern; its TDP is 75 W versus the GTS 450's 106 W.

Who should pick the GTS 450? The data shows only one scenario where it makes sense: if you have a desktop system with a PCIe 2.0 x16 slot and need a dual-slot card that draws power from a single 6-pin connector. The GTS 450 is a desktop card with fixed dimensions (210 mm length, 111 mm height), while the GTX 765M is portable-device dependent for display outputs. If you are building or upgrading a legacy desktop and cannot use an MXM module, the GTS 450 is the only one of the two that physically fits. Its 106 W TDP is higher, but it has a suggested PSU of 300 W, which is modest. The GTS 450's launch MSRP was 129 USD, but the database records no launch MSRP for the GTX 765M, so no price comparison is possible.

The verdict is not close on performance: the GTX 765M wins the only head-to-head test by a wide margin. The GTS 450's only advantage is form factor and interface compatibility for desktop users. If your system can accept an MXM module, the GTX 765M is the clear pick. If you are locked into a desktop PCIe slot, the GTS 450 remains a functional, if slower, option.

Architecture Differences

The two GPUs come from different architectural generations and process nodes. The GTX 765M uses the GK106 chip, built on Kepler architecture, on a 28 nm process from TSMC. The GTS 450 uses the GF106 chip, built on Fermi architecture, on a 40 nm process, also from TSMC. The node shrink is significant: 28 nm versus 40 nm, which explains why the GTX 765M packs more transistors into a smaller die.

Transistor counts differ sharply. The GTX 765M has 2,540 million transistors on a 221 mm² die, yielding a transistor density of 11.5 million per mm². The GTS 450 has 1,170 million transistors on a 238 mm² die, yielding just 4.9 million per mm². The GTX 765M fits more than twice the transistors into a slightly smaller area, a direct result of the newer process node.

Core configuration is also very different. The GTX 765M has 768 shading units, 64 texture mapping units, and 16 ROPs. The GTS 450 has 192 shading units, 32 TMUs, and 16 ROPs. The GTX 765M has four times the shading units and double the TMUs, while ROP count is identical. This explains the large performance gap: more shaders and more texture units mean more parallel work per clock.

Clock speeds are not directly comparable because the GTS 450 has no recorded base or boost clock, only a memory clock of 902 MHz (3.6 Gbps effective). The GTX 765M runs at a base clock of 797 MHz with a boost clock of 863 MHz, and its memory runs at 1002 MHz (4 Gbps effective). The GTX 765M's memory clock is higher, and its memory bandwidth reflects that: 64.13 GB/s versus 57.73 GB/s for the GTS 450. Both use GDDR5 memory on a 128-bit bus, but the GTX 765M's faster memory clock gives it a 11.1% bandwidth advantage.

Pixel and texture rates follow the core counts. The GTX 765M delivers 13.81 GPixel/s and 55.23 GTexel/s. The GTS 450 delivers 6.264 GPixel/s and 25.06 GTexel/s. The GTX 765M is 120.5% faster in pixel rate and 120.4% faster in texture rate. FP32 performance is similarly lopsided: 1,325.6 GFLOPS for the GTX 765M versus 601.3 GFLOPS for the GTS 450, a 120.5% advantage. Neither card has recorded FP16, RT core, or tensor core data.

API support is nearly identical: both support DirectX 12 (11_0) and OpenGL 4.6. The GTX 765M adds Vulkan 1.2.175, while the GTS 450 has no recorded Vulkan support. This is a real difference: Vulkan-capable applications will run on the GTX 765M but not on the GTS 450, based on the database records.

Physical and power characteristics differ substantially. The GTX 765M is an MXM Module with no power connectors and a 75 W TDP. The GTS 450 is a dual-slot card with one 6-pin power connector, a 106 W TDP, and a suggested PSU of 300 W. The GTS 450 has fixed dimensions of 210 mm length and 111 mm height. The GTX 765M has no recorded dimensions, as it is designed for portable devices. Display outputs: the GTX 765M is "Portable Device Dependent," while the GTS 450 offers 2x DVI and 1x mini-HDMI 1.3a.

Release timing is also a factor. The GTX 765M was released on May 29, 2013, as part of the GeForce 700M generation, succeeding GeForce 600M and preceding GeForce 800M. The GTS 450 was released on September 12, 2010, as part of the GeForce 400 generation, succeeding GeForce 200 and preceding GeForce 500. Both are end-of-life products, but the GTX 765M is nearly three years newer, which aligns with its architectural advantages.

FAQ

Q: Which GPU has higher OpenCL performance?

A: The NVIDIA GeForce GTX 765M scores 7,176 in Geekbench OpenCL, while the NVIDIA GeForce GTS 450 scores 4,893. The GTX 765M leads by 46.7%.

Q: Do both GPUs support DirectX 12?

A: Yes, both support DirectX 12 (11_0) and OpenGL 4.6. The GTX 765M additionally supports Vulkan 1.2.175, while the GTS 450 has no recorded Vulkan support.

Q: How do their memory configurations compare?

A: The GTX 765M has 2 GB of GDDR5 on a 128-bit bus with 64.13 GB/s bandwidth. The GTS 450 has 1 GB of GDDR5 on a 128-bit bus with 57.73 GB/s bandwidth. The GTX 765M has double the capacity and 11.1% more bandwidth.

Q: Which GPU uses less power?

A: The GTX 765M has a TDP of 75 W and requires no power connectors. The GTS 450 has a TDP of 106 W and requires one 6-pin connector, with a suggested PSU of 300 W.

Q: Are these GPUs still being produced?

A: No, both are end-of-life products. The GTX 765M was released in 2013, and the GTS 450 was released in 2010.

Q: Which GPU has more shading units?

A: The GTX 765M has 768 shading units, while the GTS 450 has 192. The GTX 765M has four times as many.

Where Each One Wins

The GTX 765M wins in every measurable performance category. It is 46.7% ahead in OpenCL, 120.5% ahead in FP32 throughput, 120.5% ahead in pixel rate, and 120.4% ahead in texture rate. It has more memory, higher bandwidth, more shading units, more TMUs, and a newer architecture on a smaller process node. It also draws less power (75 W versus 106 W) and requires no external power connector. For anyone running OpenCL workloads, GPU compute, or modern graphics APIs including Vulkan, the GTX 765M is the only choice.

The GTS 450's wins are confined to physical and interface compatibility. It is a desktop card with a PCIe 2.0 x16 interface, whereas the GTX 765M uses an MXM-B (3.0) bus and is portable-device dependent. The GTS 450 has fixed dimensions (210 mm length, 111 mm height) and a dual-slot form factor, making it installable in standard desktop cases. It has explicit display outputs (2x DVI, 1x mini-HDMI 1.3a), while the GTX 765M's outputs depend on the host device. If you need a standalone desktop card that plugs into a PCIe slot and outputs to DVI or HDMI directly, the GTS 450 is the practical pick, despite its lower performance.

The GTS 450 also has a recorded launch MSRP of 129 USD, while the GTX 765M has none recorded, so no price comparison is possible. The GTS 450's nearest rivals include the RTX 5060 Ti 8 GB, which shows that its average score of 4,893 is competitive with much newer hardware in synthetic tests, but that does not change the head-to-head result: the GTX 765M beats it by a wide margin.

Specification Differences

The table below lists only the fields where the two GPUs differ, based on the recorded data.

| Field | NVIDIA GeForce GTX 765M | NVIDIA GeForce GTS 450 |

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

| Chip | GK106 | GF106 |

| Architecture | Kepler | Fermi |

| Generation | GeForce 700M | GeForce 400 |

| Process Node | 28 nm | 40 nm |

| Transistors | 2,540 million | 1,170 million |

| Die Size | 221 mm² | 238 mm² |

| Transistor Density | 11.5M / mm² | 4.9M / mm² |

| Base Clock | 797 MHz | None recorded |

| Boost Clock | 863 MHz | None recorded |

| Memory Clock | 1002 MHz (4 Gbps effective) | 902 MHz (3.6 Gbps effective) |

| Memory Size | 2 GB | 1024 MB |

| Bandwidth | 64.13 GB/s | 57.73 GB/s |

| Shading Units | 768 | 192 |

| TMUs | 64 | 32 |

| Pixel Rate | 13.81 GPixel/s | 6.264 GPixel/s |

| Texture Rate | 55.23 GTexel/s | 25.06 GTexel/s |

| FP32 | 1,325.6 GFLOPS | 601.3 GFLOPS |

| TDP | 75 W | 106 W |

| Slot Width | MXM Module | Dual-slot |

| Power Connectors | None | 1x 6-pin |

| Suggested PSU | None recorded | 300 W |

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

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

| Vulkan | 1.2.175 | None recorded |

| Dimensions | None recorded | 210 mm length, 111 mm height |

| Release Date | 2013-05-29 | 2010-09-12 |

| Predecessor | GeForce 600M | GeForce 200 |

| Successor | GeForce 800M | GeForce 500 |

| Launch MSRP | None recorded | 129 USD |

| Geekbench OpenCL | 7,176 | 4,893 |

| Average Benchmark Score | 5,501 | 4,893 |

| Percentile vs. All GPUs | 32 | 28 |

The two GPUs share the same manufacturer, foundry (TSMC), memory type (GDDR5), bus width (128 bit), ROP count (16), DirectX support (12 with 11_0), and OpenGL support (4.6). Both are end-of-life. Otherwise, the GTX 765M is newer, denser, faster, and more power-efficient in every recorded metric, while the GTS 450 offers a desktop-friendly form factor with fixed outputs and a standard PCIe interface.