AMD Radeon R5 M230 vs AMD Radeon R5 M335 Comparison

The AMD Radeon R5 M335 and AMD Radeon R5 M230 are both end-of-life mobile GPUs from AMD’s Gem System generation, sharing the same GCN 1.0 architecture, 28 nm TSMC process, 690 million transistors, and a 56 mm² die size. Despite these fundamental similarities, their benchmark results show a measurable performance gap, with the M335 delivering a higher average score across available tests. This analysis uses only the provided data to compare the two parts, focusing on architectural differences, head-to-head results, and the implications for each model’s relative standing.

The Verdict

Based strictly on the data, the AMD Radeon R5 M335 is the faster part in the one head-to-head benchmark available. In the Geekbench OpenCL test, the M335 scores 4745, while the M230 scores 4577, giving the M335 a 3.7% advantage. The M335’s average benchmark score of 4752 (across two tests) also exceeds the M230’s average of 4577 (from a single test), reinforcing its edge. However, the performance difference is modest—under 4%—so real-world workloads would likely see only minor gains. The M335 sits at the 28th percentile of all GPUs, while the M230 sits at the 27th, indicating both are firmly in the lower tier of the performance spectrum, with the M335 only one percentile point higher.

For users choosing between these two, the data favors the M335 if every bit of compute performance matters, as it wins the sole head-to-head comparison. The M230, however, is not drastically behind; its 4577 OpenCL score is only 3.7% lower, and its nearest rivals include the AMD Radeon RX 560 (4569, 0.2% lower) and Intel HD Graphics P530 (4560, 0.4% lower), suggesting it is competitive with other entry-level parts. Neither GPU is suitable for demanding modern workloads—both are in the bottom third of all GPUs—so the choice between them is less about capability and more about which specific unit is available in a given system. If the M335 is present, it is the better pick; if only the M230 is available, the loss is marginal.

Architecture Differences

The two GPUs share a surprising number of architectural traits, but key differences emerge in clock speeds and derived rates. Both use the GCN 1.0 architecture, are built on a 28 nm process at TSMC, pack 690 million transistors on a 56 mm² die, and have a transistor density of 12.3M per mm². They also feature identical core counts: 320 shading units, 20 texture mapping units (TMUs), and 8 render output units (ROPs). Memory configurations match as well—2 GB of DDR3 on a 64-bit bus—though the effective memory speeds differ. The M335 runs its memory at 900 MHz (1800 Mbps effective), yielding a bandwidth of 14.40 GB/s, while the M230 runs at 1000 MHz (2 Gbps effective), producing a higher bandwidth of 16.00 GB/s. This is a notable twist: the older M230 has 11.1% more memory bandwidth (16.00 GB/s vs. 14.40 GB/s), yet it loses in compute performance.

The divergence comes from the chip clocks, though the FACT PACK lists no base or boost clocks for either GPU. Instead, the pixel rate, texture rate, and FP32 throughput reveal the underlying differences. The M335 achieves a pixel rate of 8.240 GPixel/s and a texture rate of 20.60 GTexel/s, while the M230 achieves only 4.880 GPixel/s and 12.20 GTexel/s. This translates to an FP32 compute of 659.2 GFLOPS for the M335 versus 390.4 GFLOPS for the M230—a 68.8% advantage for the M335. Since core counts are identical, these rate differences must stem from higher clock speeds on the M335’s chip (Exo) compared to the M230’s chip (Jet). The M335’s chip is listed as Exo, while the M230 uses Jet, and although both are GCN 1.0, the M335’s higher throughput suggests a more aggressively clocked design. The M230’s slot width is listed as IGP (integrated graphics processor), implying it may be more power-constrained, though no TDP figures are provided. Both support the same APIs: DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170, and both use a PCIe 3.0 x8 bus interface. Display outputs are portable-device dependent for both, and neither has power connectors (the M335 lists “None,” the M230 lists null), indicating low-power mobile designs.

Head-to-Head Benchmarks

The only direct comparison available is the Geekbench OpenCL test, where the AMD Radeon R5 M335 wins with a score of 4745 against the M230’s 4577. This is a 3.7% delta in favor of the M335. While that is the only head-to-head data point, it aligns with the broader benchmark picture: the M335’s average score of 4752 (from OpenCL at 4745 and Vulkan at 4758) is 3.8% higher than the M230’s 4577. The M335’s Vulkan score of 4758 is its best result, and it is close to its OpenCL score, suggesting consistent performance across APIs. The M230 has no Vulkan score in the pack, so no comparison is possible there.

Looking at nearest rivals provides context for each GPU’s standing. The M335’s closest competitors include the AMD Radeon R8 M445DX (4727, 0.5% lower), the AMD Radeon R5 M255 (4788, 0.7% higher), the NVIDIA GeForce RTX 3080 12 GB (4791, 0.8% higher—a surprising pairing that underscores how narrow benchmark deltas can be at this level), and the NVIDIA Quadro P400 (4684, 1.5% lower). The M230’s rivals include the AMD Radeon RX 560 (4569, 0.2% lower), Intel HD Graphics P530 (4560, 0.4% lower), NVIDIA Quadro M3000M (4621, 0.9% higher), and NVIDIA GeForce GTX 970M (4628, 1.1% higher). These deltas are all under 2%, except for the M335’s 3.7% win over the M230, meaning the gap between the two reviewed GPUs is actually larger than the gaps each has to its own nearest rivals. The M335 is 1.5% ahead of the Quadro P400 and 0.5% ahead of the R8 M445DX, while the M230 is 0.2% ahead of the RX 560 and 0.4% ahead of the Intel HD P530. This suggests the M335 occupies a slightly higher performance tier than the M230, even though both are clustered near the bottom of the GPU hierarchy.

FAQ

Q: Which GPU is faster in the head-to-head benchmark?

A: The AMD Radeon R5 M335 wins the Geekbench OpenCL test with a score of 4745 versus the M230’s 4577, a 3.7% advantage.

Q: Do the two GPUs have the same core configuration?

A: Yes, both have 320 shading units, 20 TMUs, and 8 ROPs, along with 2 GB of DDR3 memory on a 64-bit bus.

Q: How does memory bandwidth compare between the two?

A: The M230 has higher memory bandwidth at 16.00 GB/s (from 1000 MHz memory), while the M335 has 14.40 GB/s (from 900 MHz memory), a difference of 11.1% in favor of the M230.

Q: Why does the M335 perform better despite lower memory bandwidth?

A: The M335’s compute rates are much higher—659.2 GFLOPS FP32 versus 390.4 GFLOPS—which suggests higher core clocks, outweighing the M230’s memory bandwidth advantage.

Q: What are the nearest rivals for each GPU?

A: The M335’s nearest rival is the AMD Radeon R8 M445DX (0.5% lower), while the M230’s nearest rival is the AMD Radeon RX 560 (0.2% lower). Other rivals include NVIDIA parts like the Quadro P400 for the M335 and the Quadro M3000M for the M230.

Q: Are these GPUs suitable for modern applications?

A: Both sit at the 27th–28th percentile of all GPUs, indicating they are in the lower performance tier, so they would only handle light workloads.

Where Each One Wins

The AMD Radeon R5 M335 wins the only head-to-head benchmark (Geekbench OpenCL, 4745 vs. 4577) and also has a higher average benchmark score (4752 vs. 4577). Its strengths are clear in compute-heavy tasks: the FP32 throughput of 659.2 GFLOPS is 68.8% higher than the M230’s 390.4 GFLOPS, and its pixel rate (8.240 GPixel/s vs. 4.880 GPixel/s) and texture rate (20.60 GTexel/s vs. 12.20 GTexel/s) are substantially higher. This makes the M335 the better choice for any workload that leverages shading, texturing, or general-purpose compute, such as lightweight 3D rendering or OpenCL-accelerated applications. The M335 also has a Vulkan score (4758), which is its best result, indicating it can handle Vulkan-based tasks with similar efficiency.

The AMD Radeon R5 M230, despite losing the head-to-head, has one clear advantage: memory bandwidth. At 16.00 GB/s, it is 11.1% higher than the M335’s 14.40 GB/s. In memory-bound scenarios—such as tasks that stream large textures or data without heavy compute—the M230 could theoretically hold its own better than its compute rates suggest. However, the data shows no benchmark where the M230 wins; it only has a single OpenCL score (4577) and no Vulkan result. Its nearest rivals (RX 560 at 4569, Intel HD P530 at 4560) are all within 0.4% lower, meaning the M230 is competitive with those parts, but it cannot overcome the M335’s compute lead. The M230’s IGP slot width also suggests it might be integrated into a system, potentially limiting its sustained performance, though no TDP data is available to confirm. In practical terms, the M230 wins only in the narrow sense of having more memory bandwidth, but that does not translate into a benchmark victory. For any measured performance metric, the M335 is the winner, and the M230’s role is as a slightly slower alternative that still sits within 3.7% of the M335’s OpenCL score.