AMD Radeon R7 M440 vs NVIDIA GeForce MX130 Comparison

# Head-to-Head Benchmarks

The data shows a clear split between these two mobile GPUs, with each claiming one benchmark victory. In Geekbench OpenCL, the NVIDIA GeForce MX130 posts a score of 6102 against the AMD Radeon R7 M440's 5214, a decisive 17% advantage. That is the largest margin in either direction across their head-to-head tests. In Geekbench Vulkan, however, the tables turn: the AMD Radeon R7 M440 scores 5751 versus 4914 for the MX130, a 14.6% swing in AMD's favor. The overall average benchmark scores reflect how close this contest really is—the MX130 averages 5508, while the R7 M440 sits at 5483, a difference of just 0.5%. Neither GPU escapes the lower tiers of the performance spectrum; both sit at the 32nd percentile among all GPUs, meaning roughly two-thirds of the GPU market outpaces them.

Against their shared rivals, the margins are similarly narrow. The MX130 is 0.1% ahead of the NVIDIA GeForce GTX 765M (5501) and 0.7% ahead of the NVIDIA Quadro M4000 (5467). The R7 M440 is 0.3% ahead of that same Quadro M4000 and 0.7% ahead of the AMD Radeon 610M (5444). The immediate takeaway: these are not GPUs that decisively outclass their peers; they are interchangeable in raw compute terms. The OpenCL result is the biggest single win either card can claim, and it belongs to NVIDIA. The Vulkan result is nearly as large in AMD's favor, which complicates any straightforward "buy this one" narrative. For OpenCL-heavy workloads—think older compute APIs, some productivity apps—the MX130 is the clear pick. For Vulkan-based games or modern compute paths, the R7 M440 has the edge. The deltaPct values in the rival lists reinforce this: the MX130's closest rival is the GTX 765M at 0.1%, while the R7 M440's closest rival is the Quadro M4000 at 0.3%. Neither card leads its peer group by more than a fraction of a percent.

# Architecture Differences

The two GPUs come from fundamentally different design philosophies. The NVIDIA GeForce MX130 uses the GM108S chip built on the Maxwell architecture, fabricated by TSMC on a 28 nm process. It packs 1,020 million transistors into a 77 mm² die, yielding a transistor density of 13.2M per mm². The AMD Radeon R7 M440 uses the Meso chip based on GCN 3.0, also on TSMC's 28 nm node, but with a larger 125 mm² die housing 1,550 million transistors—a density of 12.4M per mm². AMD's chip is physically bigger and has more transistors, but NVIDIA's smaller die achieves higher density, a reflection of Maxwell's efficiency focus versus GCN's raw-compute orientation.

Memory configurations diverge sharply. The MX130 has 2 GB of GDDR5 on a 64-bit bus, delivering 40.10 GB/s of bandwidth. The R7 M440 has double the capacity at 4 GB, but uses DDR3 on the same 64-bit bus, resulting in only 14.40 GB/s—less than half the bandwidth. This is the single most important architectural gap. NVIDIA's memory clock is listed at 1253 MHz (5 Gbps effective), while AMD's memory runs at 900 MHz (1800 Mbps effective). For texture-heavy scenes or high-resolution assets, the MX130's bandwidth advantage is massive. For capacity-hungry workloads that need more than 2 GB, the R7 M440's 4 GB is the only option.

Compute resources also differ. The MX130 has 384 shading units, 24 texture mapping units (TMUs), and 8 raster operation units (ROPs). The R7 M440 has 320 shaders, 20 TMUs, and 8 ROPs. NVIDIA's pixel rate is 9.512 GPixel/s versus 7.128 GPixel/s for AMD; texture rate is 28.54 GTexel/s against 17.82 GTexel/s. FP32 throughput tells a similar story: 913.2 GFLOPS for the MX130, 570.2 GFLOPS for the R7 M440. Notably, the R7 M440 lists FP16 at 570.2 GFLOPS with a 1:1 ratio to FP32, while the MX130 has no FP16 listing—a sign that AMD's GCN architecture at least acknowledges half-precision compute, even if neither card is built for heavy AI workloads.

Feature support differs on the API side. The MX130 supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The R7 M440 supports DirectX 12 (12_0), OpenGL 4.6, and Vulkan 1.2.170. AMD's higher DirectX feature level (12_0 versus 11_0) and its Vulkan advantage in the benchmark suggest better modern-API compatibility, though NVIDIA's newer Vulkan revision number (1.4 versus 1.2.170) indicates a more recently updated driver stack. The bus interface also differs: the MX130 uses PCIe 3.0 x4, while the R7 M440 uses PCIe 3.0 x8. In an IGP (integrated graphics processor) form factor, this bandwidth difference rarely matters, but it is a structural distinction.

# FAQ

Q: Which GPU has higher memory bandwidth?

A: The NVIDIA GeForce MX130, with 40.10 GB/s versus 14.40 GB/s for the AMD Radeon R7 M440. This is a 2.8x advantage in raw bandwidth, driven by GDDR5 versus DDR3 memory.

Q: Does the AMD Radeon R7 M440 have more VRAM?

A: Yes. The R7 M440 comes with 4 GB, while the MX130 has 2 GB. Both use a 64-bit memory bus.

Q: Which GPU wins in OpenCL benchmarks?

A: The NVIDIA GeForce MX130 wins Geekbench OpenCL with a score of 6102 against the R7 M440's 5214, a 17% margin.

Q: Which GPU wins in Vulkan benchmarks?

A: The AMD Radeon R7 M440 wins Geekbench Vulkan with 5751 versus 4914 for the MX130, a 14.6% advantage.

Q: Do both GPUs have the same overall performance percentile?

A: Yes. Both sit at the 32nd percentile among all GPUs, and their average benchmark scores differ by only 0.5% (5508 for the MX130, 5483 for the R7 M440).

Q: What is the transistor count difference?

A: The AMD R7 M440 has 1,550 million transistors on a 125 mm² die, while the NVIDIA MX130 has 1,020 million on a 77 mm² die. AMD's chip is 48% larger in area and has 52% more transistors.

# Specification Differences

The two GPUs differ in nearly every measurable specification except for process node, foundry, ROP count, bus width, slot width, and display outputs. Both use a 28 nm TSMC process, have 8 ROPs, a 64-bit memory bus, an IGP slot form factor, and portable-device-dependent display outputs. Beyond that, the differences are extensive:

• Chip and Architecture: GM108S (Maxwell) versus Meso (GCN 3.0)
• Transistors: 1,020 million versus 1,550 million
• Die Size: 77 mm² versus 125 mm²
• Transistor Density: 13.2M / mm² versus 12.4M / mm²
• Base Clock: 1109 MHz (MX130) versus none listed (R7 M440)
• Boost Clock: 1189 MHz (MX130) versus none listed (R7 M440)
• Memory Clock: 1253 MHz / 5 Gbps effective versus 900 MHz / 1800 Mbps effective
• Memory Size: 2 GB versus 4 GB
• Memory Type: GDDR5 versus DDR3
• Memory Bandwidth: 40.10 GB/s versus 14.40 GB/s
• Shading Units: 384 versus 320
• TMUs: 24 versus 20
• Pixel Rate: 9.512 GPixel/s versus 7.128 GPixel/s
• Texture Rate: 28.54 GTexel/s versus 17.82 GTexel/s
• FP32: 913.2 GFLOPS versus 570.2 GFLOPS
• FP16: Not listed versus 570.2 GFLOPS (1:1)
• TDP: 30 W (MX130) versus none listed (R7 M440)
• Power Connectors: None (MX130) versus none listed (R7 M440)
• Bus Interface: PCIe 3.0 x4 versus PCIe 3.0 x8
• DirectX Support: 12 (11_0) versus 12 (12_0)
• Vulkan Support: 1.4 versus 1.2.170
• Release Date: 2017-11-16 versus 2016-05-14
• Predecessor: None listed versus Solar System
• Successor: None listed versus Polaris Mobile

# The Verdict

The data paints a picture of two GPUs that are statistically tied in overall performance but wildly different in specific workloads. The average benchmark scores—5508 for the MX130, 5483 for the R7 M440—differ by 0.5%, which is within the noise of any real-world usage. Both occupy the 32nd percentile of all GPUs, meaning neither is a performance part by any stretch. The choice comes down to what you value more: raw compute consistency or memory capacity.

The NVIDIA GeForce MX130 is the better compute part. It wins OpenCL by 17%, has 60% higher FP32 throughput (913.2 GFLOPS versus 570.2 GFLOPS), 60% higher texture rate (28.54 GTexel/s versus 17.82 GTexel/s), 33% higher pixel rate (9.512 GPixel/s versus 7.128 GPixel/s), and nearly 3x the memory bandwidth (40.10 GB/s versus 14.40 GB/s). It also has a listed TDP of 30 W, giving it a defined power envelope. If your workload is OpenCL-based, or if you need fast texture reads and high fill rates, the MX130 is objectively superior.

The AMD Radeon R7 M440 is the better modern-API part. It wins Vulkan by 14.6%, supports DirectX 12 (12_0) versus the MX130's 12 (11_0), and offers 4 GB of VRAM—double the MX130's 2 GB. The higher DirectX feature level and Vulkan performance suggest better headroom for newer games and compute APIs that lean on these interfaces. The 4 GB capacity also means you can load larger textures without swapping, even if the DDR3 memory is slow to feed them. If your software runs on Vulkan or if you need more than 2 GB of VRAM, the R7 M440 is the safer pick.

The release dates favor NVIDIA (late 2017 versus mid-2016), but both are end-of-life products. The R7 M440 lists a predecessor (Solar System) and successor (Polaris Mobile); the MX130 lists neither. Neither card has a launch MSRP listed, so pricing is not a factor in this analysis.

# Where Each One Wins

NVIDIA GeForce MX130 wins in:

• OpenCL compute (6102 versus 5214, 17% ahead)
• Memory bandwidth (40.10 GB/s versus 14.40 GB/s)
• Shader throughput (384 versus 320 shading units)
• Texture and pixel fill rates (28.54 GTexel/s and 9.512 GPixel/s versus 17.82 GTexel/s and 7.128 GPixel/s)
• FP32 compute (913.2 GFLOPS versus 570.2 GFLOPS)
• Defined power envelope (30 W TDP versus no listed TDP)
• Newer release date and Vulkan 1.4 driver support

AMD Radeon R7 M440 wins in:

• Vulkan compute (5751 versus 4914, 14.6% ahead)
• VRAM capacity (4 GB versus 2 GB)
• DirectX feature level (12_0 versus 11_0)
• Transistor count and die size (1,550M / 125 mm² versus 1,020M / 77 mm²)
• FP16 support (570.2 GFLOPS, 1:1 ratio)
• Wider bus interface (PCIe 3.0 x8 versus x4)
• Higher average score relative to the Quadro M4000 rival (0.3% ahead versus 0.7% ahead for the MX130)

For a builder choosing between these two, the decision is workload-driven. OpenCL productivity, texture-bound scenes, or any task that values bandwidth and fill rate points to the MX130. Vulkan gaming, DX12 titles, or workloads that exceed 2 GB of VRAM point to the R7 M440. In a pure average-score sense, they are equivalent; in practice, the right answer depends entirely on the software you run.