AMD Radeon R5 M240 vs NVIDIA GeForce 945M Comparison

Head-to-Head Benchmarks

The GeForce 945M and Radeon R5 M240 are both end-of-life mobile graphics parts, but their recorded performance in the database shows a clear separation. In the sole head-to-head benchmark, Geekbench OpenCL, the NVIDIA GeForce 945M scores 8,099 points against the AMD Radeon R5 M240’s 6,975 points. That is a 16.1% advantage for the NVIDIA part, a substantial margin for two chips aimed at similar laptop tiers.

Looking at the rival context, the GeForce 945M sits in a tight cluster. Its nearest rivals include the NVIDIA GRID K2 at 8,080 (just 0.2% behind), the AMD Radeon R9 M360 at 8,129 (0.4% ahead), and the GeForce GTX 950M at 8,135 (0.4% ahead). The 945M is effectively bracketed by these parts, meaning its 8,099 score is not an outlier but a consistent mid-range result. The Radeon R5 M240, by contrast, lands near the NVIDIA GeForce GTX 675M at 6,946 (0.4% behind) and the GTX 680M at 7,023 (0.7% ahead). Its closest competitor is the AMD FirePro M5100, which scores 6,830, putting the R5 M240 2.1% ahead of that workstation chip. The percentile data reinforces the gap: the 945M ranks at the 42nd percentile among all GPUs, while the R5 M240 sits at the 39th percentile. That three-point difference in percentile reflects a real, if modest, performance tier separation.

The delta of 16.1% in the head-to-head is the headline figure. In practical terms, a 16% lead in an OpenCL workload often translates to smoother frame rates in GPU-accelerated applications, though the margin will vary by title and driver. The database shows only this one benchmark, so the analysis must lean on that single metric, but the consistency of the rival clusters suggests the result is not a fluke. The 945M’s score is 1,124 points higher than the R5 M240’s, and that gap is larger than the difference between any of the 945M’s four nearest rivals, which all fall within a 68-point band. The R5 M240’s rivals, meanwhile, span a wider 205-point range, indicating that the AMD part’s positioning is less stable relative to its peers.

Where Each One Wins

The GeForce 945M wins the only recorded benchmark outright, so the use-case split is straightforward. For any workload that relies on OpenCL compute, the 945M is the stronger choice. Its 1,305.6 GFLOPS of FP32 throughput is nearly double the R5 M240’s 659.2 GFLOPS, and that raw compute advantage shows up directly in the Geekbench score. The 945M also has a higher pixel rate (16.32 GPixel/s vs. 8.24 GPixel/s) and texture rate (40.80 GTexel/s vs. 20.60 GTexel/s), which suggests better performance in fill-rate-bound scenarios like high-resolution textures or post-processing effects.

The Radeon R5 M240 does not win any benchmark category in the database. However, its strengths are contextual. It draws no recorded TDP figure, while the 945M is listed at 75 W, so in thin-and-light laptops where thermal headroom is scarce, the AMD part may be easier to cool despite its lower performance. The R5 M240 also uses a PCIe 3.0 x8 interface, while the 945M uses an MXM-B (3.0) bus; the MXM form factor implies a replaceable module, which is irrelevant for most end users but matters for system integrators. For legacy software that prefers GCN 1.0 architecture quirks, the AMD part might behave differently, but the database offers no benchmark evidence to support any AMD win. The verdict from the data: the 945M wins compute, fill-rate, and memory bandwidth (28.80 GB/s vs. 14.40 GB/s), while the R5 M240’s only advantages are its lower transistor count and smaller die, which are cost and power attributes, not performance ones.

Architecture Differences

The two GPUs come from fundamentally different design philosophies. The GeForce 945M is built on NVIDIA’s Maxwell architecture, chip codename GM107. It uses a 28 nm process at TSMC, with 1,870 million transistors on a 148 mm² die, yielding a transistor density of 12.6 million per mm². The Radeon R5 M240 uses AMD’s GCN 1.0 architecture, chip codename Jet, also on a 28 nm TSMC process, but with only 690 million transistors on a 56 mm² die, for a density of 12.3 million per mm². The density figures are nearly identical, which makes sense given the same node, but the absolute scale differs by a factor of 2.7 in transistor count.

The compute layout tells the story. The 945M has 640 shading units, 40 texture mapping units, and 16 raster output units. The R5 M240 has 320 shading units, 20 TMUs, and 8 ROPs. Both are exactly half the NVIDIA configuration in each category, which explains the near-2x gap in FP32, pixel rate, and texture rate. The 945M’s Maxwell architecture is also newer than GCN 1.0, and that shows in feature support: the 945M supports DirectX 12 at feature level 11_0, while the R5 M240 supports DirectX 12 at 11_1, a slightly higher feature level. Both support OpenGL 4.6, but the 945M lists Vulkan 1.4 while the R5 M240 lists Vulkan 1.2.170, meaning the NVIDIA driver stack has a newer Vulkan implementation in the database records.

Memory architecture differs as well. The 945M uses a 128-bit bus with 2 GB of DDR3, achieving 28.80 GB/s. The R5 M240 uses a 64-bit bus with 1024 MB of DDR3, achieving 14.40 GB/s. Half the bus width, half the memory size, half the bandwidth: the pattern is consistent. Both run memory at 900 MHz with 1800 Mbps effective, so the bandwidth difference is purely a function of bus width. The 945M also lists a base clock of 928 MHz and boost of 1020 MHz, while the R5 M240 runs slightly higher at 1000 MHz base and 1030 MHz boost. The AMD part has a clock advantage, but it cannot overcome the massive gap in shader count and memory bandwidth.

Specification Differences

The two parts differ in nearly every measurable specification. The GeForce 945M has a TDP of 75 W, while the Radeon R5 M240 has no recorded TDP, which is typical for a low-power mobile part but leaves a gap in the data. The 945M is an MXM Module with no power connectors, while the R5 M240 does not list a slot width or power connector type. The bus interface also differs: MXM-B (3.0) for NVIDIA, PCIe 3.0 x8 for AMD. Display outputs are listed as portable device dependent for the 945M and not listed for the R5 M240, so no comparison is possible there.

Memory capacity and bandwidth are the most user-visible differences. The 945M offers 2 GB of DDR3 on a 128-bit bus; the R5 M240 offers half that, 1024 MB, on a 64-bit bus. That means the 945M has exactly double the memory bandwidth, which is critical for texture-heavy workloads. The shading unit count (640 vs. 320), TMU count (40 vs. 20), and ROP count (16 vs. 8) all follow the same doubling pattern. The transistor count (1,870 million vs. 690 million) and die size (148 mm² vs. 56 mm²) reflect the physical scale difference. Release dates also differ: the 945M launched on 2015-10-26, while the R5 M240 launched earlier on 2014-09-17. The 945M’s predecessor is the GeForce 800M and its successor is GeForce 10 Mobile; the R5 M240’s predecessor is Solar System and its successor is Polaris Mobile.

In terms of API support, the R5 M240 has a slightly higher DirectX feature level (11_1 vs. 11_0), but the 945M has a newer Vulkan version (1.4 vs. 1.2.170). OpenGL is tied at 4.6. Neither part has ray tracing cores or tensor cores, so no comparison there. The R5 M240’s clock speeds are marginally higher (1000 MHz base vs. 928 MHz, 1030 MHz boost vs. 1020 MHz), but that is a 7.8% base clock advantage that cannot compensate for the 2x compute resource deficit.

FAQ

Q: Which GPU is faster in the recorded benchmark?

A: The NVIDIA GeForce 945M scores 8,099 in Geekbench OpenCL, which is 16.1% higher than the Radeon R5 M240’s 6,975.

Q: How does the memory bandwidth compare?

A: The 945M has 28.80 GB/s of bandwidth from a 128-bit DDR3 bus, while the R5 M240 has 14.40 GB/s from a 64-bit bus. That is exactly double.

Q: What is the difference in shading units?

A: The 945M has 640 shading units, while the R5 M240 has 320. The same 2:1 ratio applies to texture units (40 vs. 20) and ROPs (16 vs. 8).

Q: Which GPU has a higher boost clock?

A: The R5 M240 has a boost clock of 1030 MHz, which is 10 MHz higher than the 945M’s 1020 MHz boost. The R5 M240 also has a higher base clock at 1000 MHz vs. 928 MHz.

Q: Do both GPUs support DirectX 12?

A: Yes, both support DirectX 12, but at different feature levels: the 945M at 11_0 and the R5 M240 at 11_1. The R5 M240 has a slightly higher feature level.

Q: What is the transistor count difference?

A: The 945M has 1,870 million transistors on a 148 mm² die, while the R5 M240 has 690 million on a 56 mm² die. Both use a 28 nm TSMC process.

The Verdict

The data points to one clear conclusion: the NVIDIA GeForce 945M is the faster GPU. It wins the only head-to-head benchmark by 16.1%, and its specification sheet reinforces that result with double the shading units, double the ROPs, double the memory bandwidth, and nearly double the FP32 throughput. The 945M also has a higher percentile ranking (42nd vs. 39th), indicating that in the broader database of all GPUs, it sits in a slightly stronger position.

The Radeon R5 M240 is not without merit, but its advantages are not performance-based. It has a higher clock speed, a slightly higher DirectX feature level, and a smaller die that likely consumes less power, though no TDP is recorded. For a laptop where battery life and thermals are the priority and GPU performance is secondary, the R5 M240 could serve adequately. But for any user who needs OpenCL compute, gaming, or GPU-accelerated applications, the 945M is the obvious pick from the recorded data.

The rival clusters tell a similar story. The 945M trades blows with parts like the GTX 950M and R9 M360, all within 0.4% of each other, so it is a solid mid-range mobile chip. The R5 M240 sits alongside the GTX 675M and GTX 680M, which are older high-end parts but still score below the 945M’s cluster. If the choice is between these two specific GPUs, the 945M delivers more performance in every measurable category except clock speed and a single DirectX feature level. That is the practical recommendation: pick the 945M for work, pick the R5 M240 only if power constraints or system integration force the AMD part.