AMD Radeon RX 9060 XT 8 GB vs NVIDIA GeForce GTX 650 Comparison
AMD Radeon RX 9060 XT 8 GB
GeForce GTX 650
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon RX 9060 XT 8 GB vs NVIDIA GeForce GTX 650
The AMD Radeon RX 9060 XT 8 GB and the NVIDIA GeForce GTX 650 occupy radically different corners of the hardware landscape. The RX 9060 XT is an active, current-generation product built on a 4 nm process with modern RDNA 4.0 architecture, while the GTX 650 is an end-of-life Kepler part from the GeForce 600 generation. The data shows a massive generational gulf in raw specifications, yet the benchmark percentile rankings place both cards surprisingly close in the overall distribution, with the RX 9060 XT at the 24th percentile and the GTX 650 at the 22nd. This creates an unusual dynamic where the modern card utterly dominates on paper but the older card competes in aggregate scoring metrics.
The Verdict
The data presents a clear but nuanced picture. For any user running modern DirectX 12 Ultimate workloads, the AMD Radeon RX 9060 XT 8 GB is the only viable choice; the GTX 650 lacks the hardware features required for contemporary gaming. The RX 9060 XT delivers a 3DMark Steel Nomad DX12 score of 4093, positioning it 0.4% above the Intel HD Graphics 630 and 1.5% above the NVIDIA GeForce GT 755M. The GTX 650, meanwhile, has no comparable DirectX 12 benchmark score in the data; its best result is a Geekbench Vulkan score of 4524. The GTX 650's average benchmark score of 3823 places it 0.3% below the NVIDIA GeForce MX110 and 0.8% above the Intel UHD Graphics 710. The verdict is straightforward: the RX 9060 XT is for gamers and creators needing modern API support and high throughput, while the GTX 650 is strictly a legacy part for older software or basic display output. There is no scenario in the data where the GTX 650 wins a modern workload.
Architecture Differences
The architectural divide between these two GPUs is profound. The RX 9060 XT uses the Navi 44 chip based on RDNA 4.0 architecture, fabricated on a 4 nm process at TSMC. It packs 29,700 million transistors into a 199 mm² die, yielding a transistor density of 149.2M per mm². The GTX 650 uses the GK106 chip based on Kepler architecture, also from TSMC but on a much older 28 nm process. It contains just 2,540 million transistors across a larger 221 mm² die, resulting in a transistor density of only 11.5M per mm². This means the RX 9060 XT crams roughly 13 times more transistors into a physically smaller package.
The compute resources differ by an order of magnitude. The RX 9060 XT features 2048 shading units, 128 texture mapping units, 64 ROPs, and 32 dedicated ray tracing cores. The GTX 650 has 384 shading units, 32 TMUs, and 16 ROPs, with no ray tracing support whatsoever. The RX 9060 XT also supports DirectX 12 Ultimate (12_2), Vulkan 1.4, and OpenGL 4.6. The GTX 650 is limited to DirectX 12 (11_0), Vulkan 1.2.175, and OpenGL 4.6. The API gap alone disqualifies the GTX 650 from modern titles that require DX12 Ultimate features like ray tracing and mesh shaders. The RX 9060 XT also supports PCIe 5.0 x16, while the GTX 650 is limited to PCIe 3.0 x16.
Head-to-Head Benchmarks
There are no direct head-to-head benchmark entries in the data, so the comparison relies on each card's individual benchmark results and nearest rival scores. The RX 9060 XT's sole benchmark is the 3DMark Steel Nomad DX12 test, where it scores 4093. This places it 0.4% above the Intel HD Graphics 630 (4075) and 1.5% above the NVIDIA GeForce GT 755M (4033). It trails the NVIDIA Quadro K2100M by 1.4% (4151) and the AMD Radeon R5 M330 by 1.8% (4170). These are remarkably tight margins, suggesting the RX 9060 XT sits in a performance band populated by older integrated and entry-level discrete GPUs.
The GTX 650's benchmarks come from Geekbench tests: a Metal score of 2400, an OpenCL score of 4545, and a Vulkan score of 4524. Its average across these tests is 3823. Against its nearest rivals, the GTX 650 is 0.3% below the NVIDIA GeForce MX110 (3834) and 1.9% below the NVIDIA Quadro 2000 (3898). It beats the Intel UHD Graphics 710 by 0.8% (3792) and the AMD Radeon R5 Graphics by 1.5% (3883). The GTX 650's Vulkan score of 4524 exceeds the RX 9060 XT's Steel Nomad score of 4093, but these are different tests measuring different workloads, so the numbers are not directly comparable. What is comparable is the average benchmark score: the RX 9060 XT averages 4093, which is 7.1% higher than the GTX 650's 3823 average.
Specification Differences
The specification sheet reveals the full extent of the generational leap. The RX 9060 XT has a base clock of 1700 MHz, a boost clock of 3130 MHz, and a game clock of 2530 MHz; the GTX 650 lists no base or boost clocks at all. Memory configurations diverge sharply: the RX 9060 XT has 8 GB of GDDR6 on a 128-bit bus delivering 322.3 GB/s of bandwidth, while the GTX 650 has 1024 MB of GDDR5 on the same 128-bit bus but only 80.00 GB/s of bandwidth. That is a 4x difference in bandwidth and an 8x difference in capacity.
Compute throughput is similarly lopsided. The RX 9060 XT achieves 25.64 TFLOPS of FP32 performance and an equal 25.64 TFLOPS of FP16 (1:1 ratio). The GTX 650 manages just 812.5 GFLOPS of FP32 and has no listed FP16 capability. Pixel and texture rates follow the same pattern: the RX 9060 XT outputs 200.3 GPixel/s and 400.6 GTexel/s, versus 8.464 GPixel/s and 33.86 GTexel/s for the GTX 650. The RX 9060 XT draws 150 W TDP with a single 8-pin connector and a 450 W suggested PSU, while the GTX 650 sips 65 W with a 6-pin connector and a 250 W suggested PSU. The RX 9060 XT is dual-slot with HDMI 2.1b and DisplayPort 2.1a outputs; the GTX 650 is single-slot with DVI and DisplayPort 1.2. The GTX 650 measures 147 mm (5.8 inches) in length; the RX 9060 XT has no listed dimensions.
FAQ
Q: Which card has a higher average benchmark score?
A: The AMD Radeon RX 9060 XT 8 GB has an average benchmark score of 4093, which is 7.1% higher than the NVIDIA GeForce GTX 650's average of 3823.
Q: Does the GTX 650 support ray tracing?
A: No. The GTX 650 has no ray tracing cores, while the RX 9060 XT includes 32 dedicated ray tracing cores.
Q: What is the memory capacity difference?
A: The RX 9060 XT has 8 GB of GDDR6 memory, while the GTX 650 has 1024 MB (1 GB) of GDDR5 memory. The RX 9060 XT also delivers 322.3 GB/s bandwidth versus 80.00 GB/s for the GTX 650.
Q: Which card is more power efficient?
A: The GTX 650 has a 65 W TDP with a 250 W suggested PSU, while the RX 9060 XT has a 150 W TDP with a 450 W suggested PSU. The older card consumes less power, but the RX 9060 XT delivers vastly higher performance per watt given its 4 nm process.
Q: What is the production status of each card?
A: The RX 9060 XT is listed as Active production with a release date of 2025-06-03, while the GTX 650 is End-of-life with a release date of 2013-11-26 and a successor in the GeForce 700 series.
Q: How do the cards compare in percentile ranking?
A: The RX 9060 XT ranks at the 24th percentile of all GPUs, while the GTX 650 ranks at the 22nd percentile. Despite the massive specification gap, they sit within 2 percentile points of each other in the aggregate distribution.
Where Each One Wins
The RX 9060 XT wins in every modern workload category. Its DirectX 12 Ultimate support (12_2), Vulkan 1.4, and 32 ray tracing cores make it the only option for current-generation gaming, particularly titles that leverage ray tracing or mesh shaders. The 8 GB GDDR6 memory with 322.3 GB/s bandwidth handles high-resolution textures and modern game assets without the severe capacity constraints of the GTX 650's 1 GB frame buffer. The FP32 throughput of 25.64 TFLOPS versus 812.5 GFLOPS means compute-heavy applications like video encoding, machine learning inference, or CUDA-accelerated tasks (on the NVIDIA side) will see massive differences. The RX 9060 XT's PCIe 5.0 interface also ensures no bandwidth bottleneck on modern motherboards.
The GTX 650 wins in scenarios defined by legacy support and minimal power draw. Its 65 W TDP and single-slot form factor make it suitable for compact, low-power builds or as a basic display adapter for office machines. The DVI output is useful for older monitors that lack HDMI or DisplayPort. Its Geekbench Vulkan score of 4524 and OpenCL score of 4545 indicate it can still handle older API workloads at modest performance levels. For users running Windows 7-era software, DirectX 11 titles, or simple 2D desktop environments, the GTX 650's lower power requirements and smaller physical footprint give it an edge. However, the data shows the GTX 650's average score of 3823 is competitive with the RX 9060 XT's 4093 only because the two cards are benchmarked on entirely different test suites. In any shared modern workload, the RX 9060 XT's architectural advantages — 2048 shading units versus 384, 64 ROPs versus 16, and 4 nm versus 28 nm process — would produce an overwhelming victory.