AMD Radeon 880M vs NVIDIA GeForce GTX 960 Comparison

The Verdict

The data presents a clear generational divide. The AMD Radeon 880M is the decisive winner in every recorded head-to-head benchmark, posting victories by wide margins in all three shared tests. The NVIDIA GeForce GTX 960, despite being a dedicated discrete graphics card, cannot match the integrated Radeon 880M in modern workloads.

For a user building a new compact system, the AMD Radeon 880M is the obvious choice. It delivers superior raw performance, consumes far less power, and supports the latest DirectX 12 Ultimate feature set. The GTX 960 is an end-of-life product from the GeForce 900 generation, and while it holds a slight edge in the database’s aggregate percentile ranking (45th versus 43rd percentile), that advantage is not reflected in any actual benchmark where both were measured.

The GTX 960’s case is narrow. It is the only one of the two with a physical slot width (dual-slot) and a dedicated 6-pin power connector, which may be relevant for legacy system builders with older power supplies. It also has a higher average benchmark score (9273 versus 8436), but this is skewed by the GTX 960’s strong showing in Geekbench OpenCL relative to its other tests. The 880M’s average is dragged down by low Passmark DX10, DX11, and DX12 scores, which likely reflect driver or workload differences rather than overall capability.

In short, the Radeon 880M is the superior performer for modern applications. The GTX 960 is only relevant for users constrained by very specific legacy hardware requirements, and even then, the benchmark data does not favor it in any shared workload.

FAQ

Q: Which GPU wins in the 3DMark Steel Nomad DX12 test?

A: The AMD Radeon 880M wins decisively, scoring 535 versus the GTX 960’s 162, a 69.7% advantage for the 880M.

Q: How does the Geekbench Vulkan performance compare?

A: The Radeon 880M is far ahead, scoring 40006 compared to the GTX 960’s 9231. This represents a 76.9% lead for the AMD part, the largest margin in any shared benchmark.

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 960 has the higher average at 9273, versus 8436 for the AMD Radeon 880M. However, this is because the GTX 960’s Geekbench OpenCL score of 18925 is relatively high, while the 880M’s average is lowered by very low Passmark DirectX 10, 11, and 12 scores (31, 73, and 32 respectively).

Q: What are the power requirements for each card?

A: The GTX 960 has a TDP of 120 W and requires a 6-pin power connector with a suggested 300 W power supply. The Radeon 880M has a TDP of 15 W, requires no power connectors, and has no suggested PSU rating.

Q: Do both GPUs support the same DirectX version?

A: No. The GTX 960 supports DirectX 12 (12_1), while the Radeon 880M supports DirectX 12 Ultimate (12_2), which is a more advanced feature set.

Q: Which GPU is larger in physical size?

A: The GTX 960 is a dual-slot card with a length of 241 mm (9.5 inches). The Radeon 880M is an integrated GPU (IGP) with no physical slot width or dimensions listed.

Architecture Differences

The two GPUs come from entirely different eras and design philosophies. The NVIDIA GeForce GTX 960 is built on the Maxwell 2.0 architecture, using the GM206 chip, and belongs to the GeForce 900 generation. It was manufactured on a 28 nm process at TSMC. The AMD Radeon 880M, in contrast, uses the RDNA 3.5 architecture with the Strix Point chip, belonging to the Navi III IGP generation for mobile devices. It is built on a much smaller 4 nm process, also at TSMC, and was released nearly a decade later (2015 for the GTX 960, 2024 for the 880M).

The transistor counts reflect this generational gap. The GTX 960 packs 2,940 million transistors on a 228 mm² die, giving a density of 12.9 million transistors per square millimeter. The Radeon 880M integrates 34,000 million transistors on a similar 233 mm² die, achieving a density of 145.9 million per square millimeter, over 11 times higher.

The 880M features 12 ray tracing cores (RT cores), a technology completely absent from the GTX 960. This explains why the 880M supports DirectX 12 Ultimate (12_2), which includes ray tracing and other advanced features, while the GTX 960 is limited to DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4.

The memory architecture is fundamentally different. The GTX 960 uses dedicated 2 GB of GDDR5 memory on a 128-bit bus, yielding 112.2 GB/s of bandwidth. The 880M uses system shared memory, with its bus width and bandwidth being system dependent. This means the 880M’s memory performance varies based on the host system’s RAM configuration.

Specification Differences

The specification table shows clear divergences in core configuration and clock speeds. The GTX 960 has more shading units (1024 versus 768), more texture mapping units (64 versus 48), and double the ROPs (32 versus 16). However, the 880M compensates with much higher clock speeds: its boost clock is 2900 MHz versus just 1178 MHz for the GTX 960. The base clocks also differ, with the GTX 960 at 1127 MHz and the 880M at a low 400 MHz, though the 880M’s boost is far higher.

The theoretical throughput numbers favor the 880M despite fewer cores. The 880M achieves 4.454 TFLOPS of FP32 performance versus 2.413 TFLOPS for the GTX 960, nearly double. The 880M also has a 1:1 FP16 ratio at 4.454 TFLOPS, while the GTX 960 has no listed FP16 capability. The pixel rate is higher on the 880M (46.40 GPixel/s versus 37.70 GPixel/s), and the texture rate is much higher (139.2 GTexel/s versus 75.39 GTexel/s).

Power consumption is a major differentiator. The GTX 960 draws 120 W and needs a 6-pin connector, while the 880M is rated at just 15 W with no power connector required. The GTX 960 is a dual-slot card, 241 mm long, while the 880M is an IGP with no dimensions. The bus interface also differs: PCIe 3.0 x16 for the GTX 960 versus PCIe 4.0 x8 for the 880M.

Display outputs reflect their intended use. The GTX 960 has 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.2. The 880M’s outputs are listed as “Portable Device Dependent,” since it is designed for laptops and mobile systems. The GTX 960 launched with an MSRP of 199 USD, while the 880M has no listed launch MSRP as it is an integrated component.

Head-to-Head Benchmarks

The recorded data shows a clean sweep for the AMD Radeon 880M across all three tests where both GPUs were measured. The margins are substantial and consistent.

The 3DMark Steel Nomad DX12 test is a modern, demanding workload. The 880M scores 535, which is 3.3 times higher than the GTX 960’s 162. This translates to a 69.7% lead for the AMD part. This test likely stresses the newer architecture features and higher compute throughput of the 880M, which has nearly double the FP32 performance.

In Geekbench OpenCL, the 880M scores 31285 versus 18925 for the GTX 960, a 39.5% advantage. This is the closest margin of the three tests, but it is still a clear win. The GTX 960’s OpenCL result is its strongest benchmark in the entire dataset, suggesting that this workload aligns well with its Maxwell architecture. However, the 880M’s higher raw compute and better memory bandwidth from system-shared memory still give it the edge.

The Geekbench Vulkan test shows the largest gap. The 880M scores 40006, more than four times the GTX 960’s 9231. This is a 76.9% lead for the AMD part. Vulkan is a low-level API that benefits from modern hardware design and driver optimization. The 880M’s RDNA 3.5 architecture, with its 1:1 FP16 support and ray tracing cores, appears to handle Vulkan workloads far more efficiently than the older Maxwell chip.

The wins tally is unambiguous: 0 wins for the GTX 960, 3 wins for the Radeon 880M. The GTX 960’s only consolation is its higher aggregate average benchmark score, but that is a statistical artifact of having a different benchmark suite. When directly compared, the 880M dominates every single test. The data strongly suggests that for any modern application or game, the Radeon 880M is the more capable GPU, despite being an integrated solution with a fraction of the power draw.