AMD FirePro M4000 vs AMD Radeon R5 M335 Comparison

Head-to-Head Benchmarks

The single recorded comparison between these two mobile graphics parts shows a clear winner. In the Geekbench OpenCL test, the AMD FirePro M4000 scores 5537, while the AMD Radeon R5 M335 scores 4745. That puts the FirePro M4000 ahead by 16.7%, a substantial margin for a mobile GPU comparison. The FirePro M4000 wins the only head-to-head benchmark in the database, giving it one win against zero for the Radeon R5 M335.

Context from the nearest rival lists reinforces this result. The FirePro M4000 sits at the 32nd percentile among all GPUs, while the Radeon R5 M335 sits at the 28th percentile. The FirePro M4000's average benchmark score of 5537 is nearly identical to the NVIDIA GeForce MX130 (5508, just 0.5% behind) and the NVIDIA GeForce GTX 765M (5501, 0.7% behind). It also trails the NVIDIA Quadro M500M (5604) by only 1.2%. Meanwhile, the Radeon R5 M335's average score of 4752 places it within 0.5% of the AMD Radeon R8 M445DX (4727) and 1.5% ahead of the NVIDIA Quadro P400 (4684). The gap between the two AMD parts in this comparison is larger than the gap between either part and its closest rivals, meaning the FirePro M4000 and Radeon R5 M335 are not in the same performance tier at all.

The Radeon R5 M335 does have a second benchmark result, a Geekbench Vulkan score of 4758, which is nearly identical to its OpenCL score of 4745. This consistency suggests the part's compute performance is stable across different APIs. The FirePro M4000 has no Vulkan score recorded, so no cross-API comparison can be made for it. But in the one test where both parts appear, the FirePro M4000 delivers a decisive margin.

Where Each One Wins

The FirePro M4000 wins the only direct benchmark, so it is the clear choice for any workload that relies on OpenCL compute. Its 16.7% advantage over the Radeon R5 M335 translates into faster execution of general-purpose GPU tasks, which includes everything from OpenCL-accelerated rendering to scientific simulation kernels. The FirePro M4000's nearest rivals, the NVIDIA Quadro M500M and NVIDIA GeForce MX130, are within roughly 1% of its score, so it sits in a competitive band for its era. But against the Radeon R5 M335 specifically, it is unambiguously faster.

The Radeon R5 M335, by contrast, shows no benchmark win in this comparison. Its best recorded result, 4758 in Vulkan, is still below the FirePro M4000's OpenCL score. The Radeon R5 M335 does have one advantage that is not measured in raw compute scores: its 2 GB memory capacity is double the FirePro M4000's 1 GB. For workloads that require holding larger working sets in video memory, such as texture-heavy applications or larger frame buffers, the Radeon R5 M335 can potentially accommodate more data in a single pass. However, its memory interface is only 64 bit wide versus 128 bit on the FirePro M4000, and its bandwidth is dramatically lower at 14.40 GB/s compared to 64.00 GB/s. So while the Radeon R5 M335 has more storage capacity in its frame buffer, it moves data far slower, which is a serious handicap for memory-bandwidth-bound tasks.

The FirePro M4000 also wins on pixel throughput and texture throughput. Its pixel rate is 10.80 GPixel/s versus 8.240 GPixel/s for the Radeon R5 M335, a 31% advantage. Its texture rate is 21.60 GTexel/s versus 20.60 GTexel/s, a smaller but still meaningful edge. The FirePro M4000's FP32 compute is 691.2 GFLOPS versus 659.2 GFLOPS for the Radeon R5 M335, a 4.9% advantage. These figures collectively indicate that the FirePro M4000 is stronger in both fill-rate-limited and compute-limited scenarios.

Architecture Differences

Both GPUs are built on AMD's GCN 1.0 architecture and fabricated on a 28 nm process at TSMC. The FirePro M4000 uses the Chelsea chip, while the Radeon R5 M335 uses the Exo chip. The FirePro M4000 is the larger die: it measures 123 mm² and contains 1,500 million transistors. The Radeon R5 M335 is much smaller at 56 mm² with 690 million transistors. Transistor density is nearly identical, at 12.2M per mm² for the FirePro M4000 and 12.3M per mm² for the Radeon R5 M335, confirming that the performance gap comes from the FirePro M4000 having more silicon area and more compute resources, not from a denser or more efficient design.

The compute resource difference is substantial. The FirePro M4000 has 512 shading units, 32 texture mapping units, and 16 render output units. The Radeon R5 M335 has 320 shading units, 20 TMUs, and 8 ROPs. The FirePro M4000 therefore has 60% more shading units, 60% more TMUs, and double the ROP count. These raw resource advantages align with the benchmark results: the FirePro M4000's higher FP32 rating (691.2 GFLOPS versus 659.2 GFLOPS) and higher pixel rate (10.80 GPixel/s versus 8.240 GPixel/s) are direct consequences of having more execution hardware.

Memory architecture differs sharply. The FirePro M4000 uses 1024 MB of GDDR5 on a 128 bit bus, delivering 64.00 GB/s of bandwidth. The Radeon R5 M335 uses 2048 MB of DDR3 on a 64 bit bus, delivering only 14.40 GB/s. The FirePro M4000's memory clock is listed at 1000 MHz with 4 Gbps effective, while the Radeon R5 M335's memory clock is 900 MHz with 1800 Mbps effective. The FirePro M4000 has 4.4 times the memory bandwidth of the Radeon R5 M335, which is a far larger gap than the compute resource difference. This makes the FirePro M4000 especially dominant in bandwidth-sensitive workloads.

Both parts support the same API feature set: DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. Neither has dedicated ray tracing or tensor cores. The FirePro M4000 uses an MXM-A (3.0) bus interface and is an MXM Module form factor, while the Radeon R5 M335 uses PCIe 3.0 x8. The FirePro M4000 has a listed TDP of 33 W, while the Radeon R5 M335 has no TDP recorded. Both have no power connectors and portable-device-dependent display outputs.

FAQ

Q: Which GPU has the higher benchmark score?

A: The AMD FirePro M4000 scores 5537 in Geekbench OpenCL, while the AMD Radeon R5 M335 scores 4745, giving the FirePro M4000 a 16.7% lead in the only head-to-head benchmark.

Q: How do these parts compare to their closest rivals?

A: The FirePro M4000 is within 0.5% of the NVIDIA GeForce MX130 (5508) and 0.7% of the NVIDIA GeForce GTX 765M (5501), while trailing the NVIDIA Quadro M500M (5604) by 1.2%. The Radeon R5 M335 is within 0.5% of the AMD Radeon R8 M445DX (4727) and 1.5% ahead of the NVIDIA Quadro P400 (4684), while trailing the NVIDIA GeForce RTX 3080 12 GB (4791) by 0.8%.

Q: Does the Radeon R5 M335 have any advantage over the FirePro M4000?

A: Yes, it has double the memory capacity: 2048 MB versus 1024 MB. This allows it to hold larger datasets in video memory, but its memory bandwidth of 14.40 GB/s is far lower than the FirePro M4000's 64.00 GB/s.

Q: What are the core resource differences?

A: The FirePro M4000 has 512 shading units, 32 TMUs, and 16 ROPs, while the Radeon R5 M335 has 320 shading units, 20 TMUs, and 8 ROPs. The FirePro M4000 also has a larger die at 123 mm² versus 56 mm².

Q: Do both GPUs support the same APIs?

A: Yes, both support DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. Neither has ray tracing or tensor cores.

Q: Which GPU has better memory bandwidth?

A: The FirePro M4000, at 64.00 GB/s, which is 4.4 times the Radeon R5 M335's 14.40 GB/s. The FirePro M4000 also uses GDDR5 memory on a 128 bit bus, while the Radeon R5 M335 uses DDR3 on a 64 bit bus.

Specification Differences

| Specification | AMD FirePro M4000 | AMD Radeon R5 M335 |

| --- | --- | --- |

| Chip | Chelsea | Exo |

| Generation | FirePro Mobile (Mx000) | Gem System (R5 M300) |

| Transistors | 1,500 million | 690 million |

| Die Size | 123 mm² | 56 mm² |

| Transistor Density | 12.2M / mm² | 12.3M / mm² |

| Memory Clock | 1000 MHz, 4 Gbps effective | 900 MHz, 1800 Mbps effective |

| Memory Size | 1024 MB | 2048 MB |

| Memory Type | GDDR5 | DDR3 |

| Memory Bus Width | 128 bit | 64 bit |

| Memory Bandwidth | 64.00 GB/s | 14.40 GB/s |

| Shading Units | 512 | 320 |

| TMUs | 32 | 20 |

| ROPs | 16 | 8 |

| Pixel Rate | 10.80 GPixel/s | 8.240 GPixel/s |

| Texture Rate | 21.60 GTexel/s | 20.60 GTexel/s |

| FP32 | 691.2 GFLOPS | 659.2 GFLOPS |

| TDP | 33 W | Not recorded |

| Slot Width | MXM Module | Not recorded |

| Bus Interface | MXM-A (3.0) | PCIe 3.0 x8 |

| Release Date | 2012-06-26 | 2015-10-20 |

| Predecessor | FirePro Mobility | Solar System |

| Successor | Radeon Pro Mobile | Polaris Mobile |

| Avg Benchmark Score | 5537 | 4752 |

| Percentile vs All GPUs | 32 | 28 |

The Verdict

The AMD FirePro M4000 is the superior GPU by every measured performance metric. Its Geekbench OpenCL score of 5537 is 16.7% higher than the Radeon R5 M335's 4745. It delivers 691.2 GFLOPS of FP32 compute versus 659.2 GFLOPS, 10.80 GPixel/s versus 8.240 GPixel/s, and 21.60 GTexel/s versus 20.60 GTexel/s. Most strikingly, its memory bandwidth is 64.00 GB/s, which is 4.4 times the Radeon R5 M335's 14.40 GB/s. The FirePro M4000 also has double the ROPs and 60% more shading units and TMUs.

The Radeon R5 M335's only advantage is memory capacity, offering 2048 MB versus 1024 MB. That makes it suitable for applications that need a larger frame buffer but can tolerate low bandwidth. However, the 64 bit DDR3 memory interface severely limits sustained throughput, and the part's compute resources are measurably lower. The Radeon R5 M335 also has a Vulkan score of 4758, but that does not change its standing relative to the FirePro M4000.

The data points clearly toward the FirePro M4000 for anyone who prioritizes compute performance, fill rate, or memory bandwidth. Its 32nd percentile rank versus the Radeon R5 M335's 28th percentile confirms that the FirePro M4000 sits in a higher performance class overall. The Radeon R5 M335 may be a reasonable choice for workloads that require more than 1 GB of video memory and are not bandwidth-sensitive, but in a direct comparison, the FirePro M4000 is the stronger part across nearly every specification and in the only benchmark where both appear.