AMD Radeon R5 M240 vs NVIDIA GeForce GTX 650 Ti Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 650 Ti records an average benchmark score of 8053, placing it in the 42nd percentile of all GPUs. The AMD Radeon R5 M240 records an average of 6975, placing it in the 39th percentile.

Q: How large is the performance gap between the two in OpenCL workloads?

A: In the geekbench_opencl test, the GTX 650 Ti scores 7877 versus 6975 for the R5 M240, a 12.9% advantage for the NVIDIA card. This is the only head-to-head benchmark recorded in the database.

Q: Does the Radeon R5 M240 support a newer DirectX version?

A: Yes. The AMD card supports DirectX 12 (11_1), while the GTX 650 Ti supports DirectX 12 (11_0). Both cards support OpenGL 4.6, and the NVIDIA card supports Vulkan 1.2.175 versus Vulkan 1.2.170 for the AMD card.

Q: What are the memory configurations of these two GPUs?

A: Both cards have 1024 MB of memory. The GTX 650 Ti uses GDDR5 on a 128-bit bus with 86.40 GB/s of bandwidth, while the R5 M240 uses DDR3 on a 64-bit bus with 14.40 GB/s of bandwidth.

Q: Which GPU was released later?

A: The AMD Radeon R5 M240 was released on 2014-09-17, roughly two years after the NVIDIA GeForce GTX 650 Ti, which was released on 2012-10-08.

Q: How do the nearest rivals compare for each card?

A: The GTX 650 Ti's closest rival is the GTX 650 Ti Boost, which scores 8067 and is 0.2% ahead. The R5 M240's closest rival is the AMD FirePro M5100, which scores 6830 and is 2.1% behind the Radeon card.

The Verdict

The data points to a clear winner for raw compute performance. The NVIDIA GeForce GTX 650 Ti leads the AMD Radeon R5 M240 in every recorded benchmark category, with its average score of 8053 sitting 15.4% above the AMD card's 6975. In the single head-to-head OpenCL test, the NVIDIA card wins by 12.9%. The GTX 650 Ti also holds a higher percentile ranking, sitting at 42 versus 39 for the R5 M240.

For users who need maximum compute throughput, the GTX 650 Ti is the obvious choice. Its shading unit count is more than double that of the Radeon, and its memory subsystem delivers substantially higher bandwidth. The NVIDIA card also benefits from a wider 128-bit memory bus and faster GDDR5 memory. The R5 M240 does offer a slightly newer DirectX feature level (12 (11_1) versus 12 (11_0)), which could matter for certain modern titles, but that advantage does not translate into a benchmark win.

The Radeon R5 M240 is best suited for scenarios where the GTX 650 Ti cannot be used at all. The AMD card uses a PCIe 3.0 x8 interface, whereas the NVIDIA card requires PCIe 3.0 x16. For compact systems with limited electrical or physical headroom, the R5 M240's smaller die size of 56 mm² and lower transistor count of 690 million could be relevant, though the database does not record a TDP for the AMD part. The GTX 650 Ti carries a 110 W TDP, a single-slot design, and requires a 300 W suggested power supply with one 6-pin connector.

Users who prioritize compatibility with older display setups may also favor the GTX 650 Ti, which lists 2x DVI and 1x mini-HDMI 1.4a outputs; the R5 M240 has no display outputs recorded in the database. The verdict is straightforward: the GTX 650 Ti wins on performance, while the R5 M240 offers a lower-profile alternative with a newer DirectX feature set.

Head-to-Head Benchmarks

The database records a single direct comparison between these two GPUs. In the geekbench_opencl test, the NVIDIA GeForce GTX 650 Ti scores 7877, while the AMD Radeon R5 M240 scores 6975. That 902-point gap translates to a 12.9% delta in favor of NVIDIA. This result aligns with the broader compute specifications. The GTX 650 Ti delivers 1,425.4 GFLOPS of FP32 throughput, while the R5 M240 delivers 659.2 GFLOPS. The NVIDIA card is more than twice as fast in raw floating-point capability.

The pixel and texture rates tell a similar story. The GTX 650 Ti achieves 14.85 GPixel/s and 59.39 GTexel/s, versus 8.240 GPixel/s and 20.60 GTexel/s for the Radeon. The NVIDIA card leads by 80.2% in pixel rate and by 188.3% in texture rate. These figures reflect the hardware differences: the GTX 650 Ti has 768 shading units, 64 TMUs, and 16 ROPs, while the R5 M240 has 320 shading units, 20 TMUs, and 8 ROPs. The NVIDIA GPU also has a substantial memory bandwidth advantage at 86.40 GB/s versus 14.40 GB/s.

Looking at the nearest rivals reinforces the positioning. The GTX 650 Ti sits in a cluster of NVIDIA parts: the GTX 880M scores 8040 (0.2% behind), the Quadro P5000 scores 8039 (0.2% behind), the GTX 650 Ti Boost scores 8067 (0.2% ahead), and the GRID K2 scores 8080 (0.3% ahead). This places the GTX 650 Ti right in the middle of a tight performance band. The R5 M240's nearest rivals are mostly NVIDIA mobile parts: the GTX 675M scores 6946 (0.4% behind), the GTX 680M scores 7023 (0.7% ahead), the T600 scores 7035 (0.8% ahead), and the AMD FirePro M5100 scores 6830 (2.1% behind). The Radeon card sits slightly below the middle of its own cluster.

The benchmark data also shows a notable gap in the average scores of the two cards' rival groups. The GTX 650 Ti's rivals average roughly 8050, while the R5 M240's rivals average roughly 6960. This means the GTX 650 Ti competes in a performance tier that is about 15% higher than the R5 M240's tier. Users moving from the Radeon to the NVIDIA card would see a meaningful jump in compute performance, not just a marginal improvement.

Specification Differences

The two GPUs differ across nearly every major specification category. Starting with the core configuration, the GTX 650 Ti uses 768 shading units, 64 TMUs, and 16 ROPs. The R5 M240 uses 320 shading units, 20 TMUs, and 8 ROPs. The NVIDIA card has 2.4 times the shading units, 3.2 times the TMUs, and 2 times the ROPs.

Memory configurations diverge sharply. Both cards have 1024 MB of memory, but the GTX 650 Ti uses GDDR5 on a 128-bit bus, achieving 86.40 GB/s of bandwidth. The R5 M240 uses DDR3 on a 64-bit bus, achieving 14.40 GB/s. That is a 6x difference in memory bandwidth. The memory clock also differs: the GTX 650 Ti runs at 1350 MHz (5.4 Gbps effective), while the R5 M240 runs at 900 MHz (1800 Mbps effective).

The R5 M240 has explicit base and boost clocks of 1000 MHz and 1030 MHz, while the GTX 650 Ti does not have recorded base or boost clocks. Instead, the NVIDIA card's memory clock is listed at 1350 MHz. The AMD card also supports a PCIe 3.0 x8 interface, while the NVIDIA card uses PCIe 3.0 x16.

Physical specifications are largely one-sided. The GTX 650 Ti has a 145 mm (5.7 inches) length, a single-slot width, a 110 W TDP, a 300 W suggested power supply, and a 1x 6-pin power connector. The R5 M240 has no recorded dimensions, slot width, TDP, power connector, or suggested PSU. The NVIDIA card lists display outputs (2x DVI, 1x mini-HDMI 1.4a), while the AMD card has none recorded.

The release dates differ by roughly two years. The GTX 650 Ti launched on 2012-10-08 with a launch MSRP of 149 USD. The R5 M240 launched on 2014-09-17 with no launch MSRP recorded. Both cards are marked as end-of-life in the database. The NVIDIA card belongs to the GeForce 600 generation, while the AMD card belongs to the Gem System (R5 M200) generation.

Architecture Differences

The GTX 650 Ti is built on NVIDIA's Kepler architecture using the GK106S chip. The R5 M240 uses AMD's GCN 1.0 architecture with the Jet chip. Both are fabricated on a 28 nm process at TSMC, but the silicon itself is very different in scale. The GK106S contains 2,540 million transistors on a 221 mm² die, giving a transistor density of 11.5M per mm². The Jet chip contains 690 million transistors on a 56 mm² die, yielding a density of 12.3M per mm². The NVIDIA chip is 3.7 times larger by transistor count and 3.9 times larger by die area.

These architectural differences manifest directly in the compute and rendering metrics. The Kepler design allocates far more resources to shading and texturing, as seen in the 768 shading units and 64 TMUs. The GCN 1.0 design in the Jet chip is more modest, with 320 shading units and 20 TMUs. The ROP counts also differ: 16 on the NVIDIA card versus 8 on the AMD card.

The memory architecture reflects the different positioning as well. Kepler pairs the GK106S with GDDR5 over a 128-bit interface, while GCN 1.0 on the Jet chip uses DDR3 over a 64-bit interface. This is a fundamental difference in how each GPU feeds its compute units. The NVIDIA card's 86.40 GB/s bandwidth is more than sufficient for its 1,425.4 GFLOPS of FP32 throughput. The AMD card's 14.40 GB/s bandwidth is far more constrained relative to its 659.2 GFLOPS.

API support shows subtle differences. The GTX 650 Ti supports DirectX 12 (11_0), while the R5 M240 supports DirectX 12 (11_1), giving AMD a slight feature-level edge. Both support OpenGL 4.6. Vulkan versions are close: 1.2.175 for NVIDIA and 1.2.170 for AMD. Neither card has dedicated ray tracing or tensor cores recorded.

The transistor density figures are nearly identical, with the AMD chip slightly ahead at 12.3M per mm² versus 11.5M per mm². This suggests the two designs are comparable in how efficiently they pack transistors, but the NVIDIA chip simply uses far more of them. The result is a GPU that delivers roughly 2.2 times the FP32 throughput of the AMD part, with proportionally higher pixel and texture rates. The architectural choices made by each vendor led to very different performance envelopes, and the benchmark data confirms that the Kepler-based NVIDIA card offers the stronger compute package.