AMD Radeon 890M vs NVIDIA GeForce GTX 650 Ti Boost Comparison
AMD Radeon 890M
GeForce GTX 650 Ti Boost
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon 890M vs NVIDIA GeForce GTX 650 Ti Boost
Head-to-Head Benchmarks
The recorded data shows a decisive advantage for the AMD Radeon 890M in the two shared benchmark tests. In Geekbench OpenCL, the 890M scores 37,254 points against the GTX 650 Ti Boost's 9,302 points, a delta of 300.5% in favor of the AMD part. This is not a marginal win; it is a quadrupling of raw compute throughput in a compute-oriented API.
The Vulkan results follow the same pattern. The 890M posts 40,808 points, while the NVIDIA card manages 10,041 points, resulting in a 306.4% advantage for the AMD integrated processor. Vulkan is a lower-level graphics API that can expose architectural efficiency differences, and here the modern RDNA 3.5 design simply overwhelms the older Kepler architecture. The victory margin is slightly larger in Vulkan than in OpenCL, suggesting the 890M's driver overhead and hardware scheduling are particularly well-suited to modern explicit APIs.
The wins tally is 2 for the AMD Radeon 890M and 0 for the NVIDIA GeForce GTX 650 Ti Boost in head-to-head testing. There are no recorded tests where the NVIDIA card comes out ahead. The average benchmark score across all tests in the database reinforces this: the 890M averages 9,210 points, while the GTX 650 Ti Boost averages 8,067 points. The percentile rankings also favor AMD, with the 890M sitting at the 45th percentile of all GPUs and the NVIDIA part at the 42nd percentile.
One notable absence is the lack of a DirectX benchmark in the shared test set. The 890M has individual Passmark DirectX scores (33 for DX10, 73 for DX11, 37 for DX12, and 97 for DX9), while the GTX 650 Ti Boost has no comparable Passmark entries. The NVIDIA card's Metal score of 4,858 is irrelevant to the comparison since the AMD part has no Metal result, but it does indicate that the Kepler GPU can still execute modern graphics workloads when properly optimized.
Architecture Differences
The two GPUs come from vastly different eras and design philosophies. The AMD Radeon 890M is built on TSMC's 4 nm process node and uses the RDNA 3.5 architecture, specifically the Strix Point chip from the Navi III IGP generation. The NVIDIA GeForce GTX 650 Ti Boost uses the Kepler architecture with the GK106 chip on a 28 nm TSMC process. The node difference is stark: 4 nm versus 28 nm allows the 890M to pack 34,000 million transistors into a 233 mm² die, achieving a transistor density of 145.9 million per square millimeter. The GTX 650 Ti Boost contains only 2,540 million transistors on a 221 mm² die, for a density of 11.5 million per square millimeter. That is a 12.7x density advantage for the AMD part, which explains how it can offer more compute units in a similar physical footprint.
The memory architecture is fundamentally different. The 890M uses system shared memory, with its size, type, bus width, and bandwidth all listed as "System Shared" or "System Dependent." This means it relies on the host system's RAM, and performance will vary based on the platform's memory configuration. The GTX 650 Ti Boost has dedicated 2 GB of GDDR5 memory on a 192-bit bus, providing 144.2 GB/s of bandwidth. The NVIDIA card's memory clock is 1502 MHz (6 Gbps effective), whereas the 890M's memory clock is also listed as "System Shared." This is a classic integrated versus discrete trade-off: the discrete card has predictable, dedicated bandwidth, while the integrated part can potentially access more memory but with variable latency and throughput.
The compute configuration also differs significantly. The 890M has 1,024 shading units, 64 texture mapping units, and 32 ROPs, plus 16 ray tracing cores. The GTX 650 Ti Boost has 768 shading units, 64 TMUs, and 24 ROPs, with no ray tracing cores. The 890M's pixel rate is 92.80 GPixel/s and its texture rate is 185.6 GTexel/s, compared to 16.51 GPixel/s and 66.05 GTexel/s for the NVIDIA card. The FP32 throughput is 5.939 TFLOPS for the 890M versus 1.585 TFLOPS for the GTX 650 Ti Boost, and the AMD part also supports FP16 at 5.939 TFLOPS (1:1 ratio), while the NVIDIA card has no FP16 data.
The TDP figures reveal the biggest practical difference: the 890M consumes 15 W, while the GTX 650 Ti Boost draws 134 W. That is an 8.9x power differential. The 890M is an IGP with no power connectors and a PCIe 4.0 x8 interface, while the GTX 650 Ti Boost is a dual-slot card requiring a single 6-pin power connector, a 300 W suggested PSU, and a PCIe 3.0 x16 interface. The NVIDIA card measures 241 mm (9.5 inches) in length. The 890M's display outputs are "Portable Device Dependent," while the GTX 650 Ti Boost offers 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2.
Where Each One Wins
The AMD Radeon 890M wins in every measured category where both have data. Its integrated design makes it the obvious choice for thin-and-light mobile devices, given its 15 W TDP and IGP form factor. The 890M's compute capabilities are far ahead, with 3.7x the FP32 throughput and a 4x advantage in both OpenCL and Vulkan benchmarks. The presence of 16 ray tracing cores means the 890M can handle hardware-accelerated ray tracing workloads, something the GTX 650 Ti Boost cannot do at all.
The NVIDIA GeForce GTX 650 Ti Boost retains one theoretical advantage: its dedicated 2 GB GDDR5 memory with 144.2 GB/s bandwidth is not dependent on system RAM performance. In scenarios where the host system has slow or insufficient shared memory, the discrete card could maintain more consistent frame pacing. The GTX 650 Ti Boost also has a fixed 2 GB capacity, whereas the 890M's available memory is whatever the system allocates. For legacy DirectX 9 and DirectX 10 titles, the 890M's Passmark scores (97 and 33 respectively) suggest decent compatibility, but the GTX 650 Ti Boost's Kepler architecture was designed for that era and may have more mature driver paths for older APIs.
For modern workloads, the 890M is the clear winner. Its 12 Ultimate (12_2) DirectX support and Vulkan 1.4 surpass the GTX 650 Ti Boost's DirectX 12 (11_0) and Vulkan 1.2.175. The 890M's production status is "Active," while the GTX 650 Ti Boost is "End-of-life." The 890M was released in July 2024, whereas the NVIDIA card launched in March 2013. The 890M's predecessor is the Navi II IGP, and the GTX 650 Ti Boost's predecessor is the GeForce 500 series, with the GeForce 700 as its successor.
Specification Differences
The most significant specification gaps are in process node, transistor count, memory, compute units, and power. The 890M uses a 4 nm process versus 28 nm for the GTX 650 Ti Boost. The transistor counts are 34,000 million versus 2,540 million, and the die sizes are 233 mm² versus 221 mm². The 890M's transistor density is 145.9M / mm² compared to 11.5M / mm² for the NVIDIA card.
Memory specifications are entirely different: the 890M uses system shared memory with system-dependent bandwidth, while the GTX 650 Ti Boost has 2 GB GDDR5 on a 192-bit bus with 144.2 GB/s bandwidth. The 890M has 1,024 shading units, 64 TMUs, 32 ROPs, and 16 ray tracing cores; the GTX 650 Ti Boost has 768 shading units, 64 TMUs, and 24 ROPs, with no ray tracing cores. Clock speeds differ: the 890M has a 400 MHz base and 2900 MHz boost, while the GTX 650 Ti Boost has a 980 MHz base and 1032 MHz boost. The 890M's memory clock is listed as "System Shared," while the GTX 650 Ti Boost runs at 1502 MHz (6 Gbps effective).
Pixel rate is 92.80 GPixel/s for the 890M versus 16.51 GPixel/s for the GTX 650 Ti Boost. Texture rate is 185.6 GTexel/s versus 66.05 GTexel/s. FP32 is 5.939 TFLOPS versus 1.585 TFLOPS, and the 890M adds FP16 at 5.939 TFLOPS (1:1) while the GTX 650 Ti Boost has no FP16 data. TDP is 15 W versus 134 W. The 890M is an IGP with no power connectors and a PCIe 4.0 x8 interface; the GTX 650 Ti Boost is a dual-slot card with one 6-pin connector, a 300 W suggested PSU, and a PCIe 3.0 x16 interface. The 890M's display outputs are portable device dependent, while the GTX 650 Ti Boost has 2x DVI, 1x HDMI 1.4a, and 1x DisplayPort 1.2. The 890M 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.
FAQ
Q: Which GPU has the higher average benchmark score?
A: The AMD Radeon 890M averages 9,210 points across all recorded benchmarks, while the NVIDIA GeForce GTX 650 Ti Boost averages 8,067 points. The 890M also ranks at the 45th percentile of all GPUs, compared to the 42nd percentile for the NVIDIA card.
Q: What is the largest benchmark delta between the two?
A: In Geekbench Vulkan, the AMD Radeon 890M scores 40,808 versus 10,041 for the GTX 650 Ti Boost, a 306.4% advantage. The OpenCL gap is nearly identical at 300.5% in favor of the 890M.
Q: Does the GTX 650 Ti Boost have any ray tracing capability?
A: No. The GTX 650 Ti Boost has no ray tracing cores listed in its specifications. The AMD Radeon 890M includes 16 ray tracing cores.
Q: How do their power requirements compare?
A: The AMD Radeon 890M has a 15 W TDP and requires no power connectors, while the NVIDIA GeForce GTX 650 Ti Boost has a 134 W TDP and needs a single 6-pin power connector with a 300 W suggested PSU.
Q: What memory configurations do the two GPUs use?
A: The AMD Radeon 890M uses system shared memory with system-dependent bandwidth. The NVIDIA GeForce GTX 650 Ti Boost has 2 GB of dedicated GDDR5 memory on a 192-bit bus with 144.2 GB/s bandwidth.
Q: Which GPU supports newer graphics APIs?
A: The AMD Radeon 890M supports DirectX 12 Ultimate (12_2) and Vulkan 1.4. The NVIDIA GeForce GTX 650 Ti Boost supports DirectX 12 (11_0) and Vulkan 1.2.175. Both support OpenGL 4.6.
The Verdict
The data is unambiguous. The AMD Radeon 890M outperforms the NVIDIA GeForce GTX 650 Ti Boost in every shared benchmark, with deltas exceeding 300% in both OpenCL and Vulkan. It also offers superior specifications in process node, transistor density, compute units, pixel rate, texture rate, FP32 throughput, and API support, all while consuming 15 W versus 134 W. The 890M is an active product from 2024, whereas the GTX 650 Ti Boost is end-of-life from 2013.
The only areas where the GTX 650 Ti Boost could be argued to hold an edge are its dedicated 2 GB GDDR5 memory with fixed 144.2 GB/s bandwidth and its mature, driver-optimized path for legacy APIs like DirectX 9 and DirectX 10. For a user running very old games on a system with slow shared memory, the discrete card might offer more consistent performance. However, the 890M's Passmark DirectX 9 score of 97 suggests it is not incapable of handling older titles.
For anyone building a new system, the choice is clear: the AMD Radeon 890M provides dramatically better performance, modern feature support including ray tracing, and a fraction of the power draw. The NVIDIA GeForce GTX 650 Ti Boost belongs to a previous generation and cannot compete on any measured metric. The 890M is the recommended pick for general use, modern gaming, and compute workloads. The GTX 650 Ti Boost should only be considered for legacy systems where its dedicated memory and older driver ecosystem are strictly necessary.