AMD Radeon R5 M335 vs NVIDIA Quadro K3000M Comparison

Head-to-Head Benchmarks

The database records a single head-to-head benchmark between these two mobile graphics solutions: Geekbench OpenCL. In that test, the AMD Radeon R5 M335 scores 4,745 points, while the NVIDIA Quadro K3000M scores 4,241 points. That puts the AMD part 11.9% ahead of the NVIDIA part in this compute workload. The win count confirms the direction: the R5 M335 takes 1 win, the Quadro K3000M takes 0.

Looking at the broader context, the R5 M335's average benchmark score is 4,752, which places it at the 28th percentile among all GPUs in the database. Its nearest rivals include the AMD Radeon R8 M445DX at 4,727 (0.5% slower), the AMD Radeon R5 M255 at 4,788 (0.7% faster), the NVIDIA GeForce RTX 3080 12 GB at 4,791 (0.8% faster), and the NVIDIA Quadro P400 at 4,684 (1.5% slower). These are tightly clustered scores, meaning the R5 M335 sits in a very competitive mid-low tier where small performance differences separate chips.

The Quadro K3000M, by contrast, has an average benchmark score of 4,241 and sits at the 25th percentile. Its nearest rivals include the AMD Radeon Vega 3 at 4,268 (0.6% faster), the NVIDIA GeForce GTX 460M at 4,282 (1% faster), the NVIDIA GeForce GTX 1050 Ti at 4,193 (1.2% slower), and the AMD FirePro W2100 at 4,295 (1.3% faster). The K3000M's score is not dramatically lower than its rivals, but it is consistently a step behind the R5 M335 in this specific compute test.

The 11.9% delta in the head-to-head is meaningful because it represents the only direct comparison available. Neither chip is a performance leader in the database; both hover near the bottom quartile. But the R5 M335's advantage in OpenCL compute is clear and consistent with its higher average score. The K3000M's single recorded benchmark result is also its average, so there is no variation to consider.

The Verdict

The data points to the AMD Radeon R5 M335 as the better compute performer between these two. It wins the only direct benchmark by 11.9%, and its average score of 4,752 is 12.1% higher than the Quadro K3000M's 4,241. If the workload is OpenCL compute, the R5 M335 is the safer pick.

The NVIDIA Quadro K3000M, however, is not without its own merits. It carries a 75 W TDP, which is a recorded specification, and it uses GDDR5 memory on a 256-bit bus, giving it 89.60 GB/s of bandwidth. The R5 M335 uses DDR3 on a 64-bit bus, yielding 14.40 GB/s. But the benchmark data does not show a bandwidth advantage translating into a compute win for the Quadro. The recorded test results favor AMD.

For a user choosing between these two end-of-life mobile GPUs, the decision hinges on whether the application relies on OpenCL compute or on other factors like driver support or memory bandwidth. The benchmark database only records compute results, and in that realm the R5 M335 wins. If the workload is purely OpenCL-based, choose the AMD part. If the workload involves memory-heavy tasks, the Quadro's bandwidth advantage is documented, but it did not produce a higher benchmark score in the available data.

Architecture Differences

The AMD Radeon R5 M335 is built on the GCN 1.0 architecture, using the "Exo" chip, and belongs to the Gem System (R5 M300) generation. It is manufactured on a 28 nm process at TSMC, with 690 million transistors on a 56 mm² die, giving a transistor density of 12.3M per mm². The NVIDIA Quadro K3000M uses the Kepler architecture with the GK104 chip, belongs to the Quadro Kepler-M (Kx000M) generation, and is also on a 28 nm TSMC process. Its transistor count is much higher: 3,540 million on a 294 mm² die, with a density of 12.0M per mm².

The R5 M335 has 320 shading units, 20 texture mapping units, and 8 ROPs. The Quadro K3000M has 576 shading units, 48 TMUs, and 32 ROPs. Despite having fewer shading units, the R5 M335 achieves a pixel rate of 8.240 GPixel/s, slightly better than the Quadro's 7.848 GPixel/s. The Quadro has a higher texture rate at 31.39 GTexel/s versus 20.60 GTexel/s for the AMD part. In raw FP32 throughput, the Quadro leads with 753.4 GFLOPS versus 659.2 GFLOPS for the R5 M335.

The R5 M335 supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The Quadro K3000M supports DirectX 12 (11_0), OpenGL 4.6, and Vulkan 1.2.175. Both use a PCIe 3.0 interface, though the R5 M335 is listed as PCIe 3.0 x8 while the Quadro uses MXM-B (3.0). The Quadro is an MXM Module with no power connectors; the R5 M335 also has no power connectors. Both have display outputs described as "Portable Device Dependent."

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon R5 M335 has an average benchmark score of 4,752, while the NVIDIA Quadro K3000M has an average of 4,241. The R5 M335 is about 12% higher.

Q: How do the memory subsystems differ?

A: The R5 M335 uses 2 GB of DDR3 on a 64-bit bus, producing 14.40 GB/s of bandwidth. The Quadro K3000M uses 2 GB of GDDR5 on a 256-bit bus, producing 89.60 GB/s of bandwidth, which is over six times higher.

Q: Which GPU has more shading units?

A: The NVIDIA Quadro K3000M has 576 shading units, while the AMD Radeon R5 M335 has 320. The Quadro also has 48 TMUs and 32 ROPs, versus 20 TMUs and 8 ROPs for the AMD part.

Q: What are the clock speeds for each GPU?

A: The Quadro K3000M has a base and boost clock of 654 MHz. The R5 M335 does not have recorded base or boost clocks in the database; its memory clock is 900 MHz (1800 Mbps effective), while the Quadro's memory clock is 700 MHz (2.8 Gbps effective).

Q: Which GPU has a higher pixel fill rate?

A: The AMD Radeon R5 M335 achieves 8.240 GPixel/s, which is slightly higher than the Quadro K3000M's 7.848 GPixel/s, despite the Quadro having more ROPs.

Q: What is the transistor count difference?

A: The Quadro K3000M has 3,540 million transistors, while the R5 M335 has 690 million. The Quadro's die is also larger at 294 mm² versus 56 mm².

Where Each One Wins

The AMD Radeon R5 M335 wins in compute performance as measured by Geekbench OpenCL. Its score of 4,745 beats the Quadro's 4,241 by 11.9%. The R5 M335 also has a higher pixel rate (8.240 GPixel/s versus 7.848 GPixel/s) and a newer release date (October 2015 versus May 2012). Its Vulkan support is slightly older (1.2.170 vs 1.2.175), but its DirectX support is higher (12 with 11_1 feature level versus 12 with 11_0).

The NVIDIA Quadro K3000M wins in raw compute throughput metrics: it has higher FP32 performance (753.4 GFLOPS versus 659.2 GFLOPS), higher texture rate (31.39 GTexel/s versus 20.60 GTexel/s), more shading units (576 versus 320), more TMUs (48 versus 20), and more ROPs (32 versus 8). It also has vastly superior memory bandwidth (89.60 GB/s versus 14.40 GB/s) and a higher transistor count (3,540 million versus 690 million). Its TDP is recorded at 75 W, which is a defined specification, whereas the R5 M335 has no TDP listed.

The Quadro K3000M also has a slightly newer Vulkan version (1.2.175 versus 1.2.170) and a higher transistor density is nearly identical (12.0M per mm² versus 12.3M per mm², a 2.5% difference). The Quadro's bus interface is MXM-B (3.0), which is a standard for mobile workstations, while the R5 M335 uses PCIe 3.0 x8.

For users prioritizing compute benchmarks, the R5 M335 is the winner. For users prioritizing memory bandwidth or texture throughput, the Quadro K3000M has the documented advantage, though it did not translate into a higher OpenCL score.

Specification Differences

The two GPUs differ in several recorded specifications. The R5 M335 uses the "Exo" chip with GCN 1.0 architecture, while the Quadro K3000M uses the "GK104" chip with Kepler architecture. The R5 M335 belongs to the Gem System (R5 M300) generation; the Quadro belongs to Quadro Kepler-M (Kx000M). Both are 28 nm TSMC parts, but the R5 M335 has 690 million transistors versus 3,540 million for the Quadro. Die size is 56 mm² for the AMD part and 294 mm² for the NVIDIA part, with transistor densities of 12.3M per mm² and 12.0M per mm² respectively.

Clock speeds differ: the Quadro has a base and boost of 654 MHz, while the R5 M335 has no recorded base or boost clocks. Memory clocks are 900 MHz (1800 Mbps effective) for the AMD part and 700 MHz (2.8 Gbps effective) for the NVIDIA part. Memory type differs: DDR3 versus GDDR5. Bus width is 64-bit for the R5 M335 and 256-bit for the Quadro, leading to bandwidth of 14.40 GB/s versus 89.60 GB/s.

Shader resources differ significantly: the R5 M335 has 320 shading units, 20 TMUs, and 8 ROPs; the Quadro has 576 shading units, 48 TMUs, and 32 ROPs. Pixel rates are 8.240 GPixel/s for the AMD part and 7.848 GPixel/s for the NVIDIA part. Texture rates are 20.60 GTexel/s versus 31.39 GTexel/s. FP32 performance is 659.2 GFLOPS versus 753.4 GFLOPS. The Quadro has a recorded TDP of 75 W; the R5 M335 has no TDP listed. The Quadro is an MXM Module with MXM-B (3.0) interface; the R5 M335 uses PCIe 3.0 x8. Both have no power connectors and portable-device-dependent display outputs. The R5 M335 supports DirectX 12 (11_1) while the Quadro supports DirectX 12 (11_0); both support OpenGL 4.6, with Vulkan versions 1.2.170 and 1.2.175 respectively. Release dates differ: October 2015 for the AMD part, May 2012 for the NVIDIA part. Both are end-of-life products, with predecessors and successors as recorded in the database.