AMD Radeon R5 M320 vs AMD Radeon R5 M335 Comparison

The AMD Radeon R5 M335 and AMD Radeon R5 M320 are both end-of-life mobile graphics solutions from the same GCN 1.0 generation, sharing the same 28 nm TSMC process, 690 million transistors, and 56 mm² die size. Despite these fundamental similarities, benchmark data reveals a split decision: the M320 wins the OpenCL test by 6.1%, while the M335 counters with an 11.6% victory in Vulkan, resulting in a 1-1 win split and nearly identical average scores of 4752 and 4657 respectively.

Where Each One Wins

The performance profiles of these two GPUs diverge sharply depending on the API workload. In Geekbench OpenCL, the AMD Radeon R5 M320 takes a decisive lead with a score of 5051 versus the M335's 4745, a 6.1% advantage. This is the M320's strongest showing and reflects its higher memory bandwidth and clock speeds. The M320's 16.00 GB/s bandwidth and 2 Gbps effective memory rate, paired with a 780 MHz base and 855 MHz boost clock, give it a clear edge in compute-oriented OpenCL tasks. This score places it 0.6% ahead of the NVIDIA Quadro P400 (4684) and 0.8% ahead of the NVIDIA Quadro M3000M (4621) among its nearest rivals.

Conversely, the AMD Radeon R5 M335 dominates in Geekbench Vulkan, scoring 4758 against the M320's 4262 — a substantial 11.6% margin. This is the larger victory of the two head-to-head contests. The M335's Vulkan result also sits comfortably above its nearest rivals, including the AMD Radeon R8 M445DX (4727) and the NVIDIA GeForce RTX 3080 12 GB (4791, which is only 0.7% higher). The M335's 8.240 GPixel/s pixel rate and 20.60 GTexel/s texture rate, both higher than the M320's 6.840 GPixel/s and 17.10 GTexel/s, contribute to this API-specific strength.

The overall average benchmark scores tell a nuanced story: the M335 averages 4752, placing it in the 28th percentile of all GPUs, while the M320 averages 4657, landing in the 27th percentile. These are statistically close — the M335's average is only 0.5% higher than the AMD Radeon R8 M445DX (4727) and 1.5% above the NVIDIA Quadro P400 (4684). The M320's average is exactly tied with the AMD Radeon RX 9060 XT 16 GB at 4657, and it sits 0.6% behind the NVIDIA Quadro P400. Neither card offers a consistent all-around advantage; instead, each wins in a specific workload category.

Architecture Differences

Both GPUs are built on the same GCN 1.0 architecture and share identical core configurations: 320 shading units, 20 texture mapping units, and 8 ROPs. The transistor count is identical at 690 million, and both use the same 56 mm² die size, yielding a transistor density of 12.3 million per square millimeter. The manufacturing process is also the same — 28 nm at TSMC. The bus interface is PCIe 3.0 x8 for both, and both support DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170.

The key architectural differences lie in clock speeds and memory configuration. The M320 has explicit base and boost clocks of 780 MHz and 855 MHz respectively, while the M335's base and boost clocks are not specified in the data. However, the M335's compute rates tell the story: it achieves 659.2 GFLOPS FP32, 20.60 GTexel/s texture fill, and 8.240 GPixel/s pixel fill. The M320, despite its higher stated clocks, produces lower rates: 547.2 GFLOPS FP32, 17.10 GTexel/s, and 6.840 GPixel/s. This discrepancy suggests the M335's actual operating clocks may be higher than the M320's, or that the M320's boost clock is not sustained in all workloads.

Memory is where the two diverge most clearly. The M335 comes with 2 GB of DDR3 on a 64-bit bus, running at 900 MHz with 1800 Mbps effective speed, yielding 14.40 GB/s bandwidth. The M320 doubles capacity to 4 GB of DDR3 on the same 64-bit bus, but runs at 1000 MHz with 2 Gbps effective speed, producing 16.00 GB/s bandwidth — an 11% improvement. This higher memory throughput likely explains the M320's OpenCL advantage. The M320 is classified as an IGP (integrated graphics processor) with no power connectors, while the M335 lists "None" for power connectors; both are portable-device dependent for display outputs. The M320 launched earlier on 2015-05-04, while the M335 followed on 2015-10-20, both within the "Gem System (R5 M300)" generation and sharing the "Solar System" predecessor and "Polaris Mobile" successor.

The Verdict

Data-driven selection between these two GPUs depends entirely on the intended workload. For OpenCL-based compute tasks, the AMD Radeon R5 M320 is the clear choice: its 5051 score beats the M335 by 6.1%, and its 4 GB frame buffer offers double the capacity of the M335's 2 GB, which is advantageous for memory-intensive applications. The M320's 16.00 GB/s bandwidth also exceeds the M335's 14.40 GB/s, reinforcing its compute-oriented profile.

For Vulkan-based gaming or graphics workloads, the AMD Radeon R5 M335 is superior. Its 4758 Vulkan score represents an 11.6% advantage over the M320, and its higher pixel rate (8.240 GPixel/s vs 6.840 GPixel/s) and texture rate (20.60 GTexel/s vs 17.10 GTexel/s) suggest better rasterization performance. The M335's average benchmark score of 4752 is also higher than the M320's 4657, placing it in the 28th percentile versus the 27th.

Neither card is a standout in the broader GPU landscape. The M335's average is 0.8% below the NVIDIA GeForce RTX 3080 12 GB (4791) and 0.7% below the AMD Radeon R5 M255 (4788), while the M320 is tied with the AMD Radeon RX 9060 XT 16 GB (4657) and trails the NVIDIA Quadro P400 (4684) by 0.6%. Users who prioritize raw compute throughput and larger memory should opt for the M320; those who need stronger graphics API performance should choose the M335. The 1-1 win split in head-to-head benchmarks confirms that there is no universal winner — only workload-specific advantages.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R5 M335 has a higher average score of 4752, compared to the M320's 4657, representing a 2.0% difference based on the data provided.

Q: How do the two GPUs compare in OpenCL performance?

A: The AMD Radeon R5 M320 wins the Geekbench OpenCL test with a score of 5051, while the M335 scores 4745, giving the M320 a 6.1% advantage.

Q: Which GPU performs better in Vulkan workloads?

A: The AMD Radeon R5 M335 wins the Geekbench Vulkan test with a score of 4758 against the M320's 4262, a margin of 11.6% in favor of the M335.

Q: Do both GPUs have the same memory bus width?

A: Yes, both the M335 and M320 use a 64-bit memory bus, but the M320 has 4 GB of DDR3 memory while the M335 has 2 GB.

Q: What is the memory bandwidth difference between the two?

A: The M320 has a bandwidth of 16.00 GB/s at 1000 MHz memory clock, while the M335 has 14.40 GB/s at 900 MHz, making the M320's bandwidth 11% higher.

Q: Are the core configurations identical?

A: Yes, both GPUs feature 320 shading units, 20 TMUs, and 8 ROPs, but the M335 achieves higher pixel and texture rates of 8.240 GPixel/s and 20.60 GTexel/s respectively, versus the M320's 6.840 GPixel/s and 17.10 GTexel/s.

Head-to-Head Benchmarks

The two Geekbench tests provide a clear, if split, picture of performance. The first test, Geekbench OpenCL, goes to the AMD Radeon R5 M320 with a score of 5051. This is 6.1% higher than the M335's 4745, making it the M320's largest win. The margin is substantial enough to place the M320 ahead of several of its nearest rivals: it beats the NVIDIA Quadro P400 (4684) by 7.8% and the NVIDIA Quadro M3000M (4621) by 9.3%. However, the M320's OpenCL score still trails the AMD Radeon R5 M255 (4788) by 5.5% and the NVIDIA GeForce RTX 3080 12 GB (4791) by 5.4%, showing its limits against faster competitors.

The second test, Geekbench Vulkan, flips the result decisively. The AMD Radeon R5 M335 scores 4758, which is 11.6% higher than the M320's 4262. This is the largest delta in either direction. The M335's Vulkan score is particularly strong relative to its rivals: it outperforms the AMD Radeon R8 M445DX (4727) by 0.7%, the NVIDIA Quadro P400 (4684) by 1.6%, and comes within 0.7% of the NVIDIA GeForce RTX 3080 12 GB (4791). The M320's Vulkan score of 4262, by contrast, falls well below all of its listed nearest rivals, including the AMD Radeon RX 9060 XT 16 GB (4657, 9.3% higher) and the NVIDIA GeForce GTX 970M (4628, 8.6% higher).

The two tests together reveal a pattern: the M320 excels in compute-style OpenCL workloads, likely due to its higher memory bandwidth (16.00 GB/s vs 14.40 GB/s) and larger 4 GB frame buffer. The M335, despite having a lower average score, demonstrates superior graphics API performance in Vulkan, driven by its higher pixel rate (8.240 GPixel/s vs 6.840 GPixel/s) and texture rate (20.60 GTexel/s vs 17.10 GTexel/s). The FP32 compute figures align with this: the M335 produces 659.2 GFLOPS versus the M320's 547.2 GFLOPS, a 20.5% advantage that paradoxically does not translate into OpenCL dominance. Ultimately, the benchmark data shows two GPUs that are closely matched in aggregate but optimized for different API environments, with the M320 taking compute and the M335 taking graphics.