AMD Radeon 880M vs NVIDIA GeForce GTX 650 Ti Boost Comparison

The AMD Radeon 880M and NVIDIA GeForce GTX 650 Ti Boost represent two very different eras of GPU design, separated by more than a decade of architectural evolution. The 880M is a modern integrated graphics processor built on a 4 nm process, while the GTX 650 Ti Boost is a legacy discrete card from the Kepler generation on 28 nm. Benchmark data shows the 880M holds a commanding lead in the two shared tests, but the full picture requires examining where each part excels, how they compare in raw compute, and what architectural choices drive those results.

Where Each One Wins

The AMD Radeon 880M wins decisively in every benchmark where both products have comparable data. In the Geekbench OpenCL test, the 880M scores 31,285 against the GTX 650 Ti Boost’s 9,302, a delta of 236.3 percent. The Vulkan gap is even wider, with the 880M posting 40,006 versus 10,041, a 298.4 percent advantage. These are not marginal wins; they represent a generational leap in compute throughput and API efficiency.

The 880M’s win condition is rooted in its modern architecture and sheer shader throughput. It delivers 4.454 TFLOPS of FP32 performance, nearly triple the GTX 650 Ti Boost’s 1.585 TFLOPS. That raw compute advantage translates directly into superior OpenCL and Vulkan results, which are heavily dependent on shader math and parallel execution. The 880M also benefits from newer API support, including DirectX 12 Ultimate (12_2) and Vulkan 1.4, whereas the GTX 650 Ti Boost is limited to DirectX 12 (11_0) and Vulkan 1.2.175. For any modern workload using these APIs, the 880M is the clear choice.

The GTX 650 Ti Boost, however, wins in areas not captured by the head-to-head benchmark table. Its dedicated 2 GB of GDDR5 memory on a 192-bit bus delivers 144.2 GB/s of bandwidth, a figure the 880M cannot match because its memory is system-shared and bandwidth is system dependent. In scenarios where dedicated VRAM and fixed memory bandwidth matter—such as legacy games optimized for Kepler, or applications that rely on local memory latency rather than raw shader count—the GTX 650 Ti Boost remains functional. It also has a higher pixel rate of 16.51 GPixel/s, though the 880M’s 46.40 GPixel/s is nearly three times higher, so this is not a practical win. The GTX 650 Ti Boost’s advantage is purely in having a dedicated memory pool, not in speed.

The Verdict

The data is unambiguous: the AMD Radeon 880M is the faster GPU in every measurable compute benchmark shared between the two. Its average benchmark score of 8,436 places it in the 43rd percentile of all GPUs, while the GTX 650 Ti Boost’s 8,067 average sits at the 42nd percentile. The 880M also leads its nearest rivals—the NVIDIA GeForce GTX 675MX at 8,427 (0.1 percent behind) and the AMD Radeon R9 M375X at 8,325 (1.3 percent behind)—by a small but consistent margin. The GTX 650 Ti Boost’s closest competitor is the NVIDIA GRID K2 at 8,080, which is 0.2 percent behind, meaning it is effectively tied with its immediate peers.

For anyone choosing between these two today, the 880M wins on performance, efficiency, and feature support. It consumes 15 W compared to the GTX 650 Ti Boost’s 134 W, making it suitable for thin-and-light laptops without a power connector, whereas the older card requires a dual-slot cooler, a 6-pin power connector, and a 300 W suggested PSU. The 880M is also an active product, while the GTX 650 Ti Boost is end-of-life. There is no workload in the shared benchmark set where the GTX 650 Ti Boost comes out ahead.

The only reason to pick the GTX 650 Ti Boost would be for legacy system compatibility, where a PCIe 3.0 x16 slot and dedicated 2 GB VRAM might be required for older software that does not support modern IGP memory sharing. But even then, the 880M’s Vulkan score of 40,006 against 10,041 shows it is far more capable in current graphics APIs. The verdict is simple: the 880M is the superior part, and the GTX 650 Ti Boost is only relevant in niche retrofitting scenarios.

Head-to-Head Benchmarks

The two shared benchmarks tell a clear story of generational dominance. In Geekbench OpenCL, the AMD Radeon 880M scores 31,285, which is 236.3 percent higher than the GTX 650 Ti Boost’s 9,302. This test is a strong indicator of general-purpose compute performance, and the 880M’s 768 shading units, 48 TMUs, and 12 RT cores on RDNA 3.5 architecture deliver far more parallel throughput than Kepler’s 768 shading units and 64 TMUs. The GTX 650 Ti Boost’s higher TMU count (64 versus 48) does not compensate for its lower clock speeds and older instruction set, resulting in a 139.2 GTexel/s texture rate for the 880M versus 66.05 GTexel/s for the GTX 650 Ti Boost.

In Geekbench Vulkan, the gap widens to 298.4 percent, with the 880M scoring 40,006 against the GTX 650 Ti Boost’s 10,041. Vulkan is a low-overhead API that scales with hardware efficiency, and the 880M’s support for Vulkan 1.4, combined with its faster boost clock of 2,900 MHz versus 1,032 MHz, gives it a massive advantage. The GTX 650 Ti Boost’s older Vulkan 1.2.175 implementation limits its ability to fully utilize the CPU’s draw calls, while the 880M’s modern architecture handles them with ease. These results are not close; they are a rout.

Beyond the shared tests, the 880M’s own benchmark suite shows strengths in DirectX workloads. It scores 73 in Passmark DirectX 11, 32 in DirectX 12, and 97 in DirectX 9, alongside a 7,615 in Passmark G3D and 3,719 in GPU compute. The GTX 650 Ti Boost lacks comparable Passmark data, so direct comparison is impossible, but its lower OpenCL and Vulkan scores suggest it would trail in these legacy API tests as well. The 880M’s 4.454 TFLOPS FP32 throughput is the single biggest factor in these wins, providing roughly 2.8 times the compute power of the GTX 650 Ti Boost’s 1.585 TFLOPS.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon 880M has an average benchmark score of 8,436, while the NVIDIA GeForce GTX 650 Ti Boost scores 8,067. The 880M sits in the 43rd percentile of all GPUs, versus the 42nd percentile for the GTX 650 Ti Boost.

Q: How much faster is the 880M in Geekbench Vulkan?

A: The 880M scores 40,006 in Geekbench Vulkan, which is 298.4 percent higher than the GTX 650 Ti Boost’s 10,041. This is the largest performance gap in the shared benchmark set.

Q: Does the GTX 650 Ti Boost have any memory advantage?

A: Yes, the GTX 650 Ti Boost has 2 GB of dedicated GDDR5 memory on a 192-bit bus with 144.2 GB/s bandwidth. The 880M uses system-shared memory with system-dependent bandwidth, so the GTX 650 Ti Boost offers fixed local VRAM capacity.

Q: What are the power consumption differences?

A: The 880M has a TDP of 15 W and uses no power connectors, making it an integrated GPU. The GTX 650 Ti Boost has a TDP of 134 W, requires a dual-slot cooler, one 6-pin power connector, and a suggested PSU of 300 W.

Q: Which GPU supports newer graphics APIs?

A: The 880M supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The GTX 650 Ti Boost supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175, so the 880M is ahead in both DirectX and Vulkan versions.

Q: How do their nearest rivals compare?

A: The 880M’s closest rival is the NVIDIA GeForce GTX 675MX with an average score of 8,427, just 0.1 percent behind. The GTX 650 Ti Boost’s closest rival is the NVIDIA GRID K2 at 8,080, which is 0.2 percent behind, meaning both cards are tightly grouped with their immediate peers.

Architecture Differences

The AMD Radeon 880M is built on TSMC’s 4 nm process with 34,000 million transistors on a 233 mm² die, yielding a transistor density of 145.9 million per mm². It uses the RDNA 3.5 architecture with a Strix Point chip, part of the Navi III IGP generation for mobile. Its base clock is 400 MHz with a boost of 2,900 MHz, and it packs 768 shading units, 48 TMUs, 16 ROPs, and 12 ray tracing cores. FP32 performance is 4.454 TFLOPS, with FP16 at the same rate (1:1 ratio). The memory subsystem is entirely system-shared, with no dedicated VRAM, and it connects via PCIe 4.0 x8. It supports DirectX 12 Ultimate, OpenGL 4.6, and Vulkan 1.4, and is an active product released in 2024.

The NVIDIA GeForce GTX 650 Ti Boost is a 28 nm part from TSMC with 2,540 million transistors on a 221 mm² die, giving a density of just 11.5 million per mm². Its Kepler architecture uses the GK106 chip and belongs to the GeForce 600 generation. Base clock is 980 MHz with a boost of 1,032 MHz, and memory runs at 1,502 MHz with 6 Gbps effective speed. It has 768 shading units, 64 TMUs, and 24 ROPs, but no ray tracing cores. FP32 performance is 1.585 TFLOPS, and it lacks FP16 support. Memory is 2 GB of GDDR5 on a 192-bit bus with 144.2 GB/s bandwidth. It uses PCIe 3.0 x16, has display outputs of 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2, and is end-of-life, released in 2013 with a launch MSRP of 169 USD.

The architectural gap is stark: the 880M has nearly 13.4 times more transistors, a 4 nm versus 28 nm process advantage, and a boost clock nearly three times higher. The GTX 650 Ti Boost compensates with more TMUs (64 versus 48) and ROPs (24 versus 16), plus dedicated VRAM, but these cannot overcome the 880M’s superior compute density and modern feature set. The 880M’s ray tracing cores are entirely absent from the GTX 650 Ti Boost, and its Vulkan 1.4 support versus 1.2.175 further cements its position as the more future-proof part. In every architectural metric that matters for modern workloads, the 880M is the clear winner.