AMD Radeon R7 M350 vs NVIDIA GeForce GTX 750 Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 750 records an average benchmark score of 7222, placing it in the 40th percentile of all GPUs. The AMD Radeon R7 M350 averages 6327, which puts it in the 36th percentile.

Q: How do the two compare in the Geekbench OpenCL test?

A: The GTX 750 scores 9315, while the R7 M350 scores 6991. That gives the NVIDIA part a 33.2% lead in this compute workload.

Q: What about Vulkan performance?

A: The gap widens further. The GTX 750 posts 8078 in Geekbench Vulkan, versus 5662 for the R7 M350, a 42.7% advantage for the NVIDIA card.

Q: Are both GPUs built on the same manufacturing process?

A: Yes, both use a 28 nm process node at TSMC. The GTX 750 packs 1,870 million transistors on a 148 mm² die, while the R7 M350 has 1,550 million transistors on a 125 mm² die.

Q: Which GPU has more memory, and what type?

A: The R7 M350 has 4 GB of DDR3 on a 64-bit bus, while the GTX 750 has 1 GB of GDDR5 on a 128-bit bus. Despite the smaller capacity, the GTX 750's bandwidth is 80.19 GB/s, far higher than the R7 M350's 16.00 GB/s.

Q: Do both support the same level of DirectX?

A: No. The R7 M350 supports DirectX 12 (12_0), while the GTX 750 is rated for DirectX 12 (11_0). Both support OpenGL 4.6, but the GTX 750 supports Vulkan 1.4, while the R7 M350 supports Vulkan 1.2.170.

Architecture Differences

The two GPUs come from different architectural lineages. The NVIDIA GeForce GTX 750 is built on the Maxwell architecture with the GM107 chip, part of the GeForce 700 generation. The AMD Radeon R7 M350 uses the GCN 3.0 architecture with the Meso chip, from the Gem System (R7 M300) generation.

Both are fabricated at TSMC on the same 28 nm process, but the transistor counts differ meaningfully. The GTX 750 integrates 1,870 million transistors on a 148 mm² die, resulting in a transistor density of 12.6 million per mm². The R7 M350 has 1,550 million transistors on a smaller 125 mm² die, giving it a slightly lower density of 12.4 million per mm². The density figures are close, yet the NVIDIA chip has roughly 21% more transistors and 18% more die area.

The shading resources tell a similar story. The GTX 750 has 512 shading units, 32 texture mapping units, and 16 ROPs. The R7 M350 has 384 shading units, 24 TMUs, and only 8 ROPs. That is 25% fewer shading units, 25% fewer TMUs, and half the ROP count. These are structural differences that directly affect pixel throughput and texture throughput.

Memory architecture is another major split. The GTX 750 uses 1 GB of GDDR5 over a 128-bit bus, while the R7 M350 uses 4 GB of DDR3 over a 64-bit bus. The effective memory speed is 5 Gbps for the NVIDIA card versus 2 Gbps for the AMD card. This explains the enormous bandwidth gap: 80.19 GB/s for the GTX 750, only 16.00 GB/s for the R7 M350. The AMD card has four times the capacity, but the NVIDIA card has five times the bandwidth.

Clock speeds are relatively close. The GTX 750 runs at a base of 1020 MHz with a boost of 1085 MHz. The R7 M350 runs at a base of 1000 MHz with a boost of 1015 MHz. The NVIDIA part maintains a modest edge in both figures.

API support also diverges. The GTX 750 supports DirectX 12 (11_0), Vulkan 1.4, and OpenGL 4.6. The R7 M350 supports DirectX 12 (12_0), Vulkan 1.2.170, and OpenGL 4.6. The AMD card has the more modern DirectX feature level, while the NVIDIA card has the newer Vulkan version.

Head-to-Head Benchmarks

The database records two head-to-head benchmark comparisons, and the NVIDIA GeForce GTX 750 wins both.

In the Geekbench OpenCL test, the GTX 750 scores 9315 against 6991 for the R7 M350. The delta is 33.2% in favor of NVIDIA. This is a substantial margin in a compute-oriented workload. The GTX 750's higher shading unit count, wider memory bus, and higher bandwidth all contribute to this outcome. The R7 M350's 4 GB frame buffer does not help here because the workload is not capacity-bound; it is throughput-bound.

In the Geekbench Vulkan test, the gap is even wider. The GTX 750 scores 8078, while the R7 M350 scores 5662, a 42.7% difference. The NVIDIA part's Vulkan 1.4 support and superior raw throughput combine to deliver a much stronger result in this API. The R7 M350's older Vulkan 1.2.170 driver stack may also play a role, but the hardware differences are the more likely explanation.

The GTX 750's nearest rivals in the database include the AMD Radeon Vega 8 Mobile (avg score 7203, delta 0.3%), the NVIDIA GeForce GTX 560 SE (7171, delta 0.7%), the Intel Iris Pro Graphics P580 (7170, delta 0.7%), and the NVIDIA GeForce GTX 970 (7157, delta 0.9%). All of these are within 0.9% of the GTX 750's average score, which suggests that the GTX 750 sits in a tightly packed performance cluster. Its 40th percentile ranking reflects this crowded middle tier.

The R7 M350's nearest rivals include the AMD Radeon Pro WX 4100 (6330, delta 0%), the NVIDIA Quadro K620 (6282, delta 0.7%), the NVIDIA GeForce RTX 5070 Ti SUPER (6270, delta 0.9%), and the NVIDIA GeForce RTX 4070 Ti SUPER AD102 (6270, delta 0.9%). The R7 M350 is essentially tied with the Pro WX 4100, and it edges out the other three by less than 1%. Its 36th percentile ranking places it slightly below the GTX 750 in the overall distribution.

Specification Differences

The following fields differ between the two GPUs:

• Chip: GM107 (NVIDIA) versus Meso (AMD)
• Architecture: Maxwell versus GCN 3.0
• Generation: GeForce 700 versus Gem System (R7 M300)
• Transistors: 1,870 million versus 1,550 million
• Die size: 148 mm² versus 125 mm²
• Transistor density: 12.6M / mm² versus 12.4M / mm²
• Base clock: 1020 MHz versus 1000 MHz
• Boost clock: 1085 MHz versus 1015 MHz
• Memory clock: 1253 MHz (5 Gbps effective) versus 1000 MHz (2 Gbps effective)
• Memory size: 1024 MB versus 4 GB
• Memory type: GDDR5 versus DDR3
• Bus width: 128 bit versus 64 bit
• Memory bandwidth: 80.19 GB/s versus 16.00 GB/s
• Shading units: 512 versus 384
• TMUs: 32 versus 24
• ROPs: 16 versus 8
• Pixel rate: 17.36 GPixel/s versus 8.120 GPixel/s
• Texture rate: 34.72 GTexel/s versus 24.36 GTexel/s
• FP32: 1,111.0 GFLOPS versus 779.5 GFLOPS
• FP16: not specified for GTX 750 versus 779.5 GFLOPS (1:1) for R7 M350
• TDP: 55 W (GTX 750) versus not specified (R7 M350)
• Slot width: Single-slot (GTX 750) versus not specified (R7 M350)
• Power connectors: None (GTX 750) versus not specified (R7 M350)
• Suggested PSU: 250 W (GTX 750) versus not specified (R7 M350)
• Bus interface: PCIe 3.0 x16 versus PCIe 3.0 x8
• Display outputs: 2x DVI, 1x mini-HDMI 1.4a (GTX 750) versus not specified (R7 M350)
• DirectX: 12 (11_0) versus 12 (12_0)
• Vulkan: 1.4 versus 1.2.170
• Dimensions: 145 mm (5.7 inches) length for GTX 750 versus not specified for R7 M350
• Release date: 2014-02-17 versus 2015-05-04
• Predecessor: GeForce 600 versus Solar System
• Successor: GeForce 900 versus Polaris Mobile
• Launch MSRP: 119 USD (GTX 750) versus not specified (R7 M350)

Fields that are the same include the 28 nm process, TSMC foundry, OpenGL 4.6 support, and end-of-life production status.

Where Each One Wins

The NVIDIA GeForce GTX 750 wins in every recorded benchmark comparison. It is ahead by 33.2% in Geekbench OpenCL and 42.7% in Geekbench Vulkan. The raw specification sheet reinforces these results: the GTX 750 has more shading units, more TMUs, more ROPs, a wider memory bus, and dramatically higher memory bandwidth. Its pixel rate of 17.36 GPixel/s is more than double the R7 M350's 8.120 GPixel/s, and its texture rate of 34.72 GTexel/s is about 42% higher than 24.36 GTexel/s. FP32 throughput is 1,111.0 GFLOPS versus 779.5 GFLOPS, a 42.5% advantage.

The AMD Radeon R7 M350 does have one clear edge: memory capacity. With 4 GB versus 1 GB, it can hold larger textures and datasets in local memory. This could matter in workloads where capacity is the bottleneck rather than bandwidth. It also supports DirectX 12 (12_0), a more recent feature level than the GTX 750's 12 (11_0), which could matter for certain modern game features. Its FP16 throughput is equal to its FP32 throughput, at 779.5 GFLOPS, whereas the GTX 750 has no specified FP16 rate. For applications that can leverage FP16, the R7 M350 has a defined path, though the GTX 750's higher FP32 rate may still make it the stronger overall compute part.

The R7 M350 also consumes less of a system footprint in one sense: its bus interface is PCIe 3.0 x8, which is narrower than the GTX 750's PCIe 3.0 x16. That is not a performance advantage, but it may indicate a design intended for more compact or lower-power systems. The GTX 750, by contrast, is a single-slot card with no power connectors and a 55 W TDP, which makes it a straightforward drop-in for many desktops.

The Verdict

The data is unambiguous. The NVIDIA GeForce GTX 750 outperforms the AMD Radeon R7 M350 in every benchmark recorded in the database. Its average score of 7222 is 14.1% higher than the R7 M350's 6327. In the two direct comparisons, the GTX 750 leads by 33.2% in OpenCL and 42.7% in Vulkan. The specification differences align with these results: the GTX 750 has more compute units, more memory bandwidth, and higher fill rates across the board.

The R7 M350 is not without merit. Its 4 GB of memory is a genuine capacity advantage, and its DirectX 12 (12_0) support is a newer feature level than the GTX 750's 12 (11_0). For use cases that require holding large data sets in VRAM or that depend on the latest DirectX feature level, the R7 M350 has a rationale. But for raw performance, the GTX 750 is the clear pick.

A user choosing between these two should consider the workload. If the priority is compute throughput, Vulkan performance, or memory bandwidth, the GTX 750 is the obvious choice. Its 55 W TDP, single-slot design, and lack of power connectors also make it simple to install. If the priority is memory capacity or a more recent DirectX feature level, the R7 M350 may be worth considering, though its bandwidth constraints will likely limit its performance in many tasks.

The percentile rankings tell the same story from a different angle. The GTX 750 sits at the 40th percentile of all GPUs, while the R7 M350 sits at the 36th. Both are in the lower half of the distribution, but the GTX 750 is consistently above its AMD counterpart. The nearest rival data for the GTX 750 shows it trading places with parts like the Radeon Vega 8 Mobile and GeForce GTX 560 SE within a 0.9% band. The R7 M350, meanwhile, is essentially tied with the Radeon Pro WX 4100 and only slightly ahead of the Quadro K620 and RTX 5070 Ti SUPER. In short, the GTX 750 occupies a slightly higher tier of performance, and every measurement in the database confirms that ordering.