NVIDIA GeForce GTX 480 vs NVIDIA GeForce GTX 965M Comparison

# NVIDIA GeForce GTX 965M vs NVIDIA GeForce GTX 480

The NVIDIA GeForce GTX 965M and the NVIDIA GeForce GTX 480 represent two very different eras of mobile and desktop GPU design, yet benchmark results show a surprisingly close contest. In the single available head-to-head benchmark, the GeForce GTX 965M outperforms the GeForce GTX 480 by 9.1% in Geekbench OpenCL, scoring 14,509 versus 13,300. However, the GTX 480 remains a formidable desktop part with a 53rd percentile ranking among all GPUs, while the GTX 965M sits just three percentile points higher at 56. These two GPUs, separated by nearly five years of architectural evolution, deliver comparable raw compute performance despite vastly different specifications.

Head-to-Head Benchmarks

The only direct benchmark comparison available is Geekbench OpenCL, and it shows the GeForce GTX 965M taking a decisive victory. The mobile Maxwell part scores 14,509, which is 9.1% higher than the GTX 480's 13,300. This is a notable result because the GTX 480 was a flagship desktop GPU in its day, while the GTX 965M was designed for laptops and compact MXM modules. The 9.1% advantage translates into a real-world edge in compute workloads that leverage OpenCL, such as video encoding, physics simulation, and certain rendering tasks.

Looking at the broader competitive landscape, the GTX 965M's average benchmark score of 14,404 places it just ahead of several integrated and entry-level discrete solutions. It edges out the AMD Radeon RX Vega 11 by 0.1%, the NVIDIA GeForce GTX TITAN by 0.2%, the AMD Radeon Vega 11 by 0.4%, and the Intel Iris Xe MAX Graphics by 0.6%. The margins here are razor-thin, indicating that the GTX 965M sits in a tightly contested performance band where even small architectural advantages matter.

The GTX 480, with an average score of 13,300, finds itself in a similar competitive cluster but slightly lower. It trails the AMD Radeon Pro 555X by 0.2%, the AMD FirePro M6100 by 0.4%, the AMD Radeon RX 5500M by 0.4%, and the AMD Radeon HD 8950M by 0.6%. This grouping of mobile and professional GPUs around the 13,300-13,400 score range suggests that the GTX 480's raw compute capability remains competitive with much newer parts, even if its feature set and efficiency are dated.

Where Each One Wins

The GeForce GTX 965M wins the compute benchmark outright, but the nature of its victory is more about efficiency and architecture than raw brute force. With 1,024 shading units running at a 924 MHz base clock and 950 MHz boost, the GTX 965M achieves 1.946 TFLOPS of FP32 performance. This is significantly higher than the GTX 480's 1,345 GFLOPS, which comes from 480 shading units. The Maxwell architecture's ability to extract more performance per shader and per clock cycle is evident in these numbers.

Where the GTX 965M truly excels is in its memory subsystem efficiency relative to its power envelope. It uses a 128-bit memory bus with 2 GB of GDDR5 running at 1,253 MHz (5 Gbps effective), delivering 80.19 GB/s of bandwidth. While this is less than half the GTX 480's bandwidth, the GTX 965M still manages to outperform it in compute tasks, demonstrating that Maxwell 2.0's memory compression and scheduling improvements compensate for narrower buses.

The GTX 480, on the other hand, wins in the memory bandwidth category outright. Its 384-bit bus with 1,536 MB of GDDR5 at 924 MHz (3.7 Gbps effective) provides 177.4 GB/s, more than double the GTX 965M's bandwidth. This makes the GTX 480 better suited for bandwidth-intensive workloads that scale with raw memory throughput, such as large texture streaming, high-resolution framebuffer operations, and certain scientific computing tasks. Additionally, the GTX 480 has 48 ROPs compared to the GTX 965M's 32, giving it a theoretical pixel rate advantage of 21.03 GPixel/s versus 30.40 GPixel/s for the 965M — though the newer card still wins on pixel rate despite fewer ROPs due to higher clocks.

Architecture Differences

The architectural gulf between these two GPUs is substantial. The GeForce GTX 965M is built on the GM204 chip using Maxwell 2.0 architecture, fabricated on TSMC's 28 nm process. It packs 5,200 million transistors into a 398 mm² die, yielding a transistor density of 13.1 million transistors per square millimeter. In contrast, the GeForce GTX 480 uses the GF100 chip with Fermi architecture on TSMC's older 40 nm process, containing 3,100 million transistors across a larger 529 mm² die, resulting in just 5.9 million transistors per square millimeter.

This process advantage is the root of many downstream differences. The 28 nm node allows for higher clock speeds at lower power draw, which is why the GTX 965M can achieve 924 MHz base and 950 MHz boost clocks despite being a mobile part. The GTX 480 has no listed base or boost clock for its core, but its memory runs at 924 MHz (3.7 Gbps effective), which is lower than the GTX 965M's 1,253 MHz (5 Gbps effective) memory clock.

The shader architecture also differs fundamentally. The GTX 965M features 1,024 shading units, 64 texture mapping units, and 32 ROPs. The GTX 480 has 480 shading units, 60 TMUs, and 48 ROPs. Maxwell 2.0's design emphasizes higher shader counts and better instruction-level parallelism, while Fermi's design was more focused on raw throughput per shader. The result is that the GTX 965M achieves 60.80 GTexel/s of texture fill rate versus the GTX 480's 42.06 GTexel/s, and 30.40 GPixel/s versus 21.03 GPixel/s.

API support also separates these parts. The GTX 965M supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4, making it compatible with modern gaming and compute APIs. The GTX 480 supports DirectX 12 (11_0) and OpenGL 4.6 but has no Vulkan support listed. This means the GTX 480 cannot take advantage of Vulkan's low-overhead benefits in modern titles or compute applications.

Form factor and power delivery highlight the mobile-versus-desktop divide. The GTX 965M comes as an MXM Module with no power connectors and a bus interface of MXM-B (3.0), designed for laptops. The GTX 480 is a dual-slot desktop card measuring 267 mm (10.5 inches) in length, requiring a 250 W TDP, one 6-pin and one 8-pin power connector, and a 600 W suggested power supply. It outputs video via 2x DVI and 1x mini-HDMI 1.3a, while the GTX 965M's display outputs are described as "Portable Device Dependent."

The Verdict

The data clearly favors the GeForce GTX 965M for most modern use cases. It wins the only head-to-head benchmark by 9.1%, offers modern API support including Vulkan 1.4 and DirectX 12 (12_1), and delivers higher texture and pixel fill rates. For anyone using OpenCL compute workloads or playing modern games that leverage DirectX 12 or Vulkan, the GTX 965M is the superior choice despite being a mobile part.

The GTX 480 retains relevance only in scenarios where raw memory bandwidth is paramount. Its 177.4 GB/s of bandwidth is more than double the GTX 965M's 80.19 GB/s, making it potentially better for specific bandwidth-limited tasks. However, its lack of Vulkan support and older DirectX 12 (11_0) feature level limit its usefulness in contemporary software. Its 250 W TDP and 600 W suggested power supply also make it impractical for most modern systems, especially compared to the GTX 965M's power connector-free MXM design.

The percentile rankings reinforce this assessment. The GTX 965M sits at the 56th percentile of all GPUs, while the GTX 480 sits at the 53rd. This three-point difference, combined with the 9.1% benchmark lead, suggests that the GTX 965M is the more capable overall GPU. The GTX 480's nearest rivals are all mobile or professional parts with similar scores, indicating that its performance class has been absorbed by more efficient designs over time.

FAQ

Q: Which GPU is faster in Geekbench OpenCL?

A: The NVIDIA GeForce GTX 965M scores 14,509, which is 9.1% higher than the GeForce GTX 480's 13,300.

Q: What are the memory bandwidth specifications for each GPU?

A: The GTX 965M has 80.19 GB/s of bandwidth from a 128-bit bus with 2 GB GDDR5, while the GTX 480 has 177.4 GB/s from a 384-bit bus with 1536 MB GDDR5.

Q: Does the GeForce GTX 480 support Vulkan?

A: No, the GTX 480 has no Vulkan support listed. The GTX 965M supports Vulkan 1.4.

Q: How do their transistor counts and die sizes compare?

A: The GTX 965M has 5,200 million transistors on a 398 mm² die using 28 nm process, while the GTX 480 has 3,100 million transistors on a 529 mm² die using 40 nm process.

Q: What is the power consumption difference?

A: The GTX 480 has a 250 W TDP and requires a 600 W suggested power supply, while the GTX 965M has no listed TDP and uses no external power connectors.

Q: Which GPU has a higher texture fill rate?

A: The GTX 965M achieves 60.80 GTexel/s, which is higher than the GTX 480's 42.06 GTexel/s.