AMD Radeon HD 8790M vs NVIDIA GeForce MX130 Comparison

# Where Each One Wins

The benchmark data splits these two mobile GPUs cleanly by workload type. The AMD Radeon HD 8790M takes the Vulkan compute test decisively, while the NVIDIA GeForce MX130 dominates in OpenCL. Each card wins one of the two recorded head-to-head tests, making this a genuine toss-up depending on which API the application uses.

Looking at the raw scores, the MX130 posts a Geekbench OpenCL result of 6102 against the HD 8790M's 5017, a margin of 17.8% in NVIDIA's favor. That is a substantial lead for OpenCL-based workloads, which include many productivity applications, video encoding tools, and scientific compute tasks. The MX130 also holds a modest advantage in raw FP32 throughput, with 913.2 GFLOPS versus 691.2 GFLOPS for the AMD card, which helps explain its OpenCL superiority.

The AMD card reverses the situation in the Vulkan test. The HD 8790M scores 6365 against the MX130's 4914, a 29.5% advantage. Vulkan is a lower-level graphics and compute API, and this result suggests that AMD's GCN 1.0 architecture handles Vulkan workloads more efficiently than NVIDIA's Maxwell design, despite the MX130's higher clock speeds and texture throughput.

The average benchmark scores tell a more nuanced story. The HD 8790M averages 5691 across both tests, while the MX130 averages 5508. That puts the AMD card about 3.3% ahead on average, though the MX130 sits at the 32nd percentile of all GPUs while the HD 8790M sits at the 33rd percentile—effectively identical positions in the overall distribution. In practical terms, neither card offers a universal performance advantage; the winner depends almost entirely on whether the application uses OpenCL or Vulkan.

# Architecture Differences

The two cards come from different architectural generations and vendors, and those differences show up throughout their specifications. The HD 8790M uses AMD's GCN 1.0 architecture on the Mars chip, while the MX130 uses NVIDIA's Maxwell architecture on the GM108S chip. Both are built on the same 28 nm process at TSMC, and both have a die size of 77 mm². The transistor counts are close, with the MX130 at 1,020 million and the HD 8790M at 950 million, giving the NVIDIA chip a slightly higher transistor density of 13.2M per mm² versus 12.3M per mm².

The memory subsystems differ significantly. The HD 8790M uses a 128-bit memory bus with 64.00 GB/s of bandwidth, while the MX130 uses a 64-bit bus with 40.10 GB/s. Both have 2 GB of GDDR5 memory, but the AMD card's wider bus gives it nearly 60% more memory bandwidth. This could matter in texture-heavy games or compute tasks that are bandwidth-limited. The MX130 compensates with faster effective memory clocks: 5 Gbps effective versus 4 Gbps effective for the HD 8790M.

Core counts are identical at 384 shading units, 24 texture mapping units, and 8 raster output pipelines. The MX130 runs at much higher clocks, with a base of 1109 MHz and boost of 1189 MHz, compared to the HD 8790M's 850 MHz base and 900 MHz boost. This clock advantage drives the MX130's higher pixel rate of 9.512 GPixel/s versus 7.200 GPixel/s, and its higher texture rate of 28.54 GTexel/s versus 21.60 GTexel/s.

The form factors and interfaces also differ. The HD 8790M ships as an MXM module using the MXM-A (3.0) interface, while the MX130 is an integrated GPU package on PCIe 3.0 x4. The MX130 has a specified TDP of 30 W, while the HD 8790M has no TDP listed. Both use no external power connectors. In terms of API support, the HD 8790M supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170, while the MX130 supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.4. The NVIDIA card has a newer Vulkan version, but the AMD card supports a higher DirectX feature level.

# Head-to-Head Benchmarks

The Geekbench OpenCL test is the MX130's strongest showing. It scores 6102 against the HD 8790M's 5017, a difference of 1085 points that translates to a 17.8% advantage. This is a substantial gap that would be noticeable in any OpenCL-accelerated application, from video editors to physics simulations. The MX130's higher FP32 throughput and clock speeds likely drive this result, as OpenCL workloads often scale with raw compute throughput.

The Vulkan test flips the script entirely. The HD 8790M scores 6365 against the MX130's 4914, a difference of 1451 points and a 29.5% margin. This is an even larger relative advantage than the MX130's OpenCL lead, and it suggests that the AMD card is particularly strong in Vulkan compute or graphics workloads. The HD 8790M's wider memory bus may play a role here, as Vulkan applications often access memory differently than OpenCL ones.

Looking at the nearest rivals provides context for these scores. The HD 8790M's average score of 5691 places it within 1% of the Intel Iris Pro Graphics P6300 (5712, -0.4% delta), the NVIDIA GeForce GTX 670MX (5721, -0.5% delta), and the NVIDIA GeForce GTX 550 Ti (5731, -0.7% delta). It also beats the NVIDIA Quadro M500M (5604) by 1.6%. The MX130's average of 5508 sits within 1% of the NVIDIA GeForce GTX 765M (5501, 0.1% delta), the AMD Radeon R7 M440 (5483, 0.5% delta), and the NVIDIA Quadro M4000 (5467, 0.7% delta), while trailing the AMD FirePro M4000 (5537) by 0.5%. These tight margins show that both cards are squarely in the same performance tier, with neither offering a meaningful overall advantage over the other.

# FAQ

Q: Which GPU is faster overall?

A: The AMD Radeon HD 8790M has a slightly higher average benchmark score of 5691 across both tests, compared to the NVIDIA GeForce MX130's 5508. However, each card wins one test, and their percentiles are nearly identical at 33rd and 32nd, respectively.

Q: Which card is better for OpenCL workloads?

A: The NVIDIA GeForce MX130 scores 6102 in Geekbench OpenCL, beating the HD 8790M's 5017 by 17.8%. This makes the MX130 the clear choice for OpenCL-accelerated applications.

Q: Which card wins in Vulkan?

A: The AMD Radeon HD 8790M scores 6365 in Geekbench Vulkan, beating the MX130's 4914 by 29.5%. AMD's card has a decisive advantage in this API.

Q: Do the cards have the same memory bandwidth?

A: No. The HD 8790M has a 128-bit memory bus with 64.00 GB/s bandwidth, while the MX130 has a 64-bit bus with 40.10 GB/s. Both use 2 GB of GDDR5 memory.

Q: How do the core configurations compare?

A: Both cards have 384 shading units, 24 TMUs, and 8 ROPs. The MX130 runs at higher clocks (1109 MHz base, 1189 MHz boost) compared to the HD 8790M (850 MHz base, 900 MHz boost).

Q: What are the form factor differences?

A: The HD 8790M is an MXM module using the MXM-A (3.0) interface, while the MX130 is an integrated GPU package on PCIe 3.0 x4. The MX130 has a TDP of 30 W, while the HD 8790M has no TDP listed.

# Specification Differences

The following specifications differ between the two cards:

• Manufacturer: AMD versus NVIDIA
• Chip: Mars versus GM108S
• Architecture: GCN 1.0 versus Maxwell
• Generation: Solar System (HD 8700M) versus GeForce MX (1xx)
• Transistors: 950 million versus 1,020 million
• Transistor Density: 12.3M / mm² versus 13.2M / mm²
• Base Clock: 850 MHz versus 1109 MHz
• Boost Clock: 900 MHz versus 1189 MHz
• Memory Clock: 1000 MHz / 4 Gbps effective versus 1253 MHz / 5 Gbps effective
• Memory Bus Width: 128 bit versus 64 bit
• Memory Bandwidth: 64.00 GB/s versus 40.10 GB/s
• Pixel Rate: 7.200 GPixel/s versus 9.512 GPixel/s
• Texture Rate: 21.60 GTexel/s versus 28.54 GTexel/s
• FP32: 691.2 GFLOPS versus 913.2 GFLOPS
• TDP: Not listed versus 30 W
• Slot Width: MXM Module versus IGP
• Bus Interface: MXM-A (3.0) versus PCIe 3.0 x4
• DirectX Support: 12 (11_1) versus 12 (11_0)
• Vulkan Support: 1.2.170 versus 1.4
• Release Date: 2013-03-31 versus 2017-11-16

# The Verdict

The data points to a clear conclusion: choose based on the application programming interface you intend to use. For OpenCL-heavy workloads, the NVIDIA GeForce MX130 is the superior option, offering a 17.8% performance advantage. For Vulkan-based applications, the AMD Radeon HD 8790M is the better choice by a 29.5% margin. Neither card is a universal winner.

The MX130's strengths lie in its higher clock speeds, FP32 throughput, and texture rate. Its 913.2 GFLOPS of FP32 compute is about 32% higher than the HD 8790M's 691.2 GFLOPS, and its 1189 MHz boost clock is nearly a third faster. These attributes make it the better pick for OpenCL compute tasks.

The HD 8790M's strengths are its wider memory bus and Vulkan performance. The 128-bit bus provides 64.00 GB/s of bandwidth, which is 60% more than the MX130's 40.10 GB/s. The 29.5% Vulkan advantage suggests that AMD's architecture is better optimized for this newer API, despite the older release date.

For buyers who run a mix of workloads, the HD 8790M's slightly higher average score of 5691 and marginally better percentile (33rd versus 32nd) give it a thin edge. However, the MX130's newer release date and 30 W TDP make it a more modern, power-efficient option in mobile systems. The production status of both is end-of-life, so availability may be limited. Ultimately, the choice hinges on which API dominates the user's application library, as the benchmark data shows these cards are otherwise closely matched.