NVIDIA GeForce 945M vs NVIDIA GeForce GTX 465 Comparison

Where Each One Wins

The recorded benchmark data splits cleanly between these two NVIDIA parts, though the split is heavily one-sided. The NVIDIA GeForce GTX 465 wins the only head-to-head benchmark recorded in the database, the Geekbench OpenCL test, with a score of 9294 against the GeForce 945M's 8099. That is a 14.8% advantage for the older desktop card. The win count reflects this: the GTX 465 holds 1 win, while the 945M holds 0 wins in direct comparison.

However, the use-case split is not simply about which card is faster in raw compute. The GTX 465 belongs to the GeForce 400 generation, a desktop-oriented part with a 200 W TDP, dual-slot cooling, and power connectors. The 945M belongs to the GeForce 900M generation, a mobile-oriented part with a 75 W TDP, MXM module form factor, and no power connectors. The data suggests the GTX 465 is the choice for stationary systems where compute throughput is the priority, while the 945M is the choice for portable devices where the display outputs are described as "Portable Device Dependent" and the power draw is dramatically lower.

The percentile rankings reinforce this split. The GTX 465 sits at the 46th percentile among all GPUs in the database, while the 945M sits at the 42nd percentile. Neither card is a top-tier performer, but the GTX 465's position is noticeably higher. Its nearest rivals include the GeForce GTX 850M (0.1% behind), the AMD Radeon R7 M380 (0.2% behind), and the GeForce GTX 960 (0.2% ahead). The 945M's nearest rivals include the NVIDIA GRID K2 (0.2% behind), the AMD Radeon R9 M360 (0.4% ahead), and the GeForce GTX 950M (0.4% ahead). These proximity bands show that both cards operate in a similar performance neighborhood, but the GTX 465 edges ahead.

Architecture Differences

The architectural gap between these two cards spans five years of NVIDIA design evolution. The GTX 465 uses the GF100 chip on the Fermi architecture, built on a 40 nm process at TSMC. The 945M uses the GM107 chip on the Maxwell architecture, also fabricated by TSMC but on a 28 nm process. The transistor counts tell a story of efficiency: the GF100 packs 3,100 million transistors on a 529 mm² die, yielding a density of 5.9M per mm². The GM107 packs 1,870 million transistors on a much smaller 148 mm² die, yielding a density of 12.6M per mm². The Maxwell chip achieves more than double the transistor density of the Fermi chip.

The compute configurations differ in ways that reflect their eras. The GTX 465 has 352 shading units, 44 texture mapping units, and 32 ROPs. The 945M has 640 shading units, 40 TMUs, and 16 ROPs. Despite having fewer shading units, the GTX 465 produces a pixel rate of 13.38 GPixel/s versus the 945M's 16.32 GPixel/s, and a texture rate of 26.75 GTexel/s versus 40.80 GTexel/s. The raw FP32 throughput favors the Maxwell part: 1,305.6 GFLOPS for the 945M versus 855.4 GFLOPS for the GTX 465. This is a case where the newer architecture extracts more performance per transistor, yet the older card still wins the actual OpenCL benchmark.

Memory architecture is another major divergence. The GTX 465 uses 1024 MB of GDDR5 on a 256-bit bus, delivering 102.7 GB/s of bandwidth. The 945M uses 2 GB of DDR3 on a 128-bit bus, delivering only 28.80 GB/s. The GTX 465 has nearly four times the memory bandwidth, which likely contributes to its OpenCL victory despite the 945M's higher shader count and FP32 rating. Clock speeds also differ: the 945M has a base clock of 928 MHz and a boost clock of 1020 MHz, while the GTX 465 has no base or boost clock recorded, only a memory clock of 802 MHz (3.2 Gbps effective). The 945M's memory runs at 900 MHz (1800 Mbps effective).

Feature support shows a mixed picture. Both cards support DirectX 12 (11_0) and OpenGL 4.6. The 945M adds Vulkan 1.4 support, while the GTX 465 has no Vulkan support recorded. The GTX 465 offers display outputs of 2x DVI and 1x mini-HDMI 1.3a, whereas the 945M's outputs are listed as "Portable Device Dependent," reflecting its mobile nature.

The Verdict

The data points to a clear but nuanced verdict. For raw OpenCL compute, the NVIDIA GeForce GTX 465 is the winner, posting 9294 points against the 945M's 8099, a 14.8% advantage. The GTX 465 also holds the higher percentile ranking at 46 versus 42. If the task is compute-heavy and the system can accommodate a 200 W dual-slot card with 2x 6-pin power connectors and a 550 W suggested PSU, the GTX 465 is the superior choice based on the recorded measurements.

For mobile or low-power applications, the 945M is the only viable option from this pair. Its 75 W TDP, MXM module form factor, and lack of power connectors make it suitable for portable devices. Its 2 GB memory capacity is double the GTX 465's 1 GB, and its 640 shading units outnumber the GTX 465's 352. The 945M also supports Vulkan 1.4, which the GTX 465 does not. The data cannot declare an overall winner because the form factors serve different purposes. The database shows that the GTX 465 wins the direct benchmark, but the 945M wins on efficiency, memory capacity, and modern API support.

FAQ

Q: Which GPU has the higher OpenCL benchmark score?

A: The NVIDIA GeForce GTX 465 scores 9294, which is 14.8% higher than the GeForce 945M's 8099.

Q: How much memory does each card have and what type?

A: The GTX 465 has 1024 MB of GDDR5, while the 945M has 2 GB of DDR3.

Q: What is the TDP difference between the two cards?

A: The GTX 465 has a TDP of 200 W, while the 945M has a TDP of 75 W.

Q: Which card supports Vulkan?

A: The GeForce 945M supports Vulkan 1.4. The GeForce GTX 465 has no Vulkan support recorded in the database.

Q: How do their nearest rivals compare?

A: The GTX 465's closest rival is the GeForce GTX 850M, which is 0.1% behind. The 945M's closest rival is the NVIDIA GRID K2, which is 0.2% behind.

Q: What are the memory bandwidth figures?

A: The GTX 465 delivers 102.7 GB/s, while the 945M delivers 28.80 GB/s.

Head-to-Head Benchmarks

The single recorded head-to-head benchmark is Geekbench OpenCL, and it favors the GTX 465 decisively. The GTX 465 scores 9294, while the 945M scores 8099. The delta is 14.8%, a substantial margin that places the older Fermi card well ahead of the newer Maxwell part in this specific test. The result is consistent with the GTX 465's percentile ranking of 46 versus the 945M's 42, and it aligns with the GTX 465's nearest rival cluster, which includes the GeForce GTX 960 at 0.2% ahead and the GeForce GTX 850M at 0.1% behind.

The 945M's nearest rival cluster tells a different story. It sits among the NVIDIA GRID K2 (0.2% behind), the AMD Radeon R9 M360 (0.4% ahead), and the GeForce GTX 950M (0.4% ahead). These deltas are all smaller than 1%, indicating that the 945M is tightly grouped with its competition. The GTX 465's cluster is similarly tight, with all deltas under 1% as well. But the gap between the two cards themselves, 14.8%, is far larger than the gaps to their respective rivals.

The benchmark result implies that memory bandwidth may be the deciding factor. The GTX 465's 102.7 GB/s bandwidth dwarfs the 945M's 28.80 GB/s. Even though the 945M has nearly double the shading units (640 versus 352) and significantly higher FP32 throughput (1,305.6 GFLOPS versus 855.4 GFLOPS), the OpenCL workload appears to favor the card with superior memory throughput. The pixel rate also leans toward the 945M (16.32 GPixel/s versus 13.38 GPixel/s), yet the real-world test still lands in the GTX 465's favor. This suggests that the GTX 465's 256-bit bus and GDDR5 memory provide a decisive advantage in compute tasks that the 945M's 128-bit DDR3 configuration cannot overcome.

Specification Differences

The two cards differ across nearly every specification category. The GTX 465 uses the GF100 chip on Fermi architecture, fabricated on a 40 nm process, while the 945M uses the GM107 chip on Maxwell architecture, fabricated on a 28 nm process. Transistor counts are 3,100 million versus 1,870 million, and die sizes are 529 mm² versus 148 mm². Transistor density is 5.9M per mm² for the GTX 465 and 12.6M per mm² for the 945M.

The GTX 465 has 352 shading units, 44 TMUs, and 32 ROPs. The 945M has 640 shading units, 40 TMUs, and 16 ROPs. Pixel rates are 13.38 GPixel/s for the GTX 465 and 16.32 GPixel/s for the 945M. Texture rates are 26.75 GTexel/s versus 40.80 GTexel/s. FP32 performance is 855.4 GFLOPS versus 1,305.6 GFLOPS.

Memory configurations differ substantially. The GTX 465 has 1024 MB of GDDR5 on a 256-bit bus with 102.7 GB/s bandwidth. The 945M has 2 GB of DDR3 on a 128-bit bus with 28.80 GB/s bandwidth. The GTX 465's memory clock is 802 MHz (3.2 Gbps effective), while the 945M's is 900 MHz (1800 Mbps effective). The 945M has a base clock of 928 MHz and a boost clock of 1020 MHz; the GTX 465 has no base or boost clock recorded.

Power and physical specifications are also distinct. The GTX 465 draws 200 W, requires a dual-slot cooler, uses 2x 6-pin power connectors, and suggests a 550 W PSU. The 945M draws 75 W, uses an MXM module form factor, and has no power connectors. The GTX 465 measures 241 mm (9.5 inches) in length; the 945M has no dimensions recorded. The GTX 465 uses PCIe 2.0 x16, while the 945M uses MXM-B (3.0). Display outputs are 2x DVI and 1x mini-HDMI 1.3a for the GTX 465, versus "Portable Device Dependent" for the 945M.

API support is identical for DirectX (12 (11_0)) and OpenGL (4.6), but the 945M adds Vulkan 1.4 while the GTX 465 has none. Release dates differ by over five years: the GTX 465 launched on 2010-05-30, and the 945M on 2015-10-26. The GTX 465 has a launch MSRP of 279 USD; the 945M has no recorded launch MSRP. The GTX 465's predecessor is GeForce 200 and successor is GeForce 500, while the 945M's predecessor is GeForce 800M and successor is GeForce 10 Mobile. Both are end-of-life products.