AMD Radeon R5 M320 vs NVIDIA GeForce GT 745M Comparison

FAQ

Q: Which GPU has the higher average benchmark score in the database?

A: The AMD Radeon R5 M320 records an average benchmark score of 4657, while the NVIDIA GeForce GT 745M scores 3953. This places the AMD part at the 27th percentile of all GPUs, above the GT 745M’s 23rd percentile ranking.

Q: How do the two compare in the OpenCL benchmark?

A: The Radeon R5 M320 leads decisively in Geekbench OpenCL, scoring 5051 against the GT 745M’s 3580. That is a 41.1% advantage for the AMD GPU in this particular test.

Q: Does the NVIDIA GeForce GT 745M win any benchmark?

A: Yes. In the Geekbench Vulkan test, the GT 745M scores 5502, which is 22.5% higher than the Radeon R5 M320’s 4262. The two GPUs split the head-to-head record at one win each.

Q: What memory configurations do these cards use?

A: The AMD Radeon R5 M320 comes with 4 GB of DDR3 memory on a 64-bit bus, delivering 16.00 GB/s of bandwidth. The NVIDIA GeForce GT 745M uses 2 GB of GDDR5 memory on a 128-bit bus, providing 64.00 GB/s of bandwidth.

Q: What are the core counts of each GPU?

A: The Radeon R5 M320 has 320 shading units, 20 texture mapping units, and 8 ROPs. The GeForce GT 745M has 384 shading units, 32 texture mapping units, and 16 ROPs.

Q: Which GPU was released earlier?

A: The NVIDIA GeForce GT 745M was released on March 31, 2013, while the AMD Radeon R5 M320 came later, on May 4, 2015. Both are now classified as end-of-life products.

Architecture Differences

The AMD Radeon R5 M320 is built on the GCN 1.0 architecture using the Jet chip, manufactured by TSMC on a 28 nm process. The GPU integrates 690 million transistors on a 56 mm² die, giving it a transistor density of 12.3 million transistors per square millimeter. It belongs to AMD’s Gem System generation, part of the R5 M300 family, and its predecessor is the Solar System, with the successor listed as Polaris Mobile.

The NVIDIA GeForce GT 745M uses the Kepler architecture with the GK107 chip, also built by TSMC at 28 nm. Its die is substantially larger at 118 mm² and packs 1,270 million transistors, though the density is slightly lower at 10.8 million transistors per square millimeter. The GT 745M belongs to the GeForce 700M generation, succeeding the GeForce 600M and preceding the GeForce 800M.

Both GPUs share the same 28 nm process and TSMC foundry, but the architectural philosophies diverge. The Radeon R5 M320’s GCN design prioritizes raw shader throughput per area: it achieves a higher FP32 rate of 547.2 GFLOPS with fewer shading units (320) at a base clock of 780 MHz and boost clock of 855 MHz. The Kepler-based GT 745M, in contrast, runs with more shading units (384) but reports no base or boost clocks in the database; its FP32 output is 421.6 GFLOPS, lower than the AMD part despite having more execution resources.

Memory architecture is another major split. The Radeon R5 M320 uses 4 GB of DDR3 on a 64-bit bus, yielding 16.00 GB/s of bandwidth. The GT 745M uses 2 GB of GDDR5 on a 128-bit bus, quadrupling bandwidth to 64.00 GB/s. The NVIDIA part’s memory clock is listed at 1000 MHz with 4 Gbps effective data rate, while the AMD part also runs at 1000 MHz but only 2 Gbps effective. This bandwidth gap is the most striking architectural difference and explains much of the Vulkan performance disparity.

The bus interface also differs: the Radeon R5 M320 connects via PCIe 3.0 x8, while the GT 745M uses PCIe 3.0 x16. Both are integrated-class GPUs (IGP slot width) with portable-device-dependent display outputs. API support is close, with both supporting DirectX 12 (the AMD part at 11_1 feature level, the NVIDIA at 11_0), OpenGL 4.6, and Vulkan (1.2.170 for AMD, 1.2.175 for NVIDIA). The GT 745M additionally has a Geekbench Metal score of 2777, a test the Radeon M320 does not appear in.

The Verdict

The data paints a split picture. The AMD Radeon R5 M320 is the stronger choice for workloads that favor OpenCL compute, where it beats the GT 745M by 41.1%. It also carries twice the memory capacity at 4 GB, which may matter for applications that need larger framebuffers, even if that memory is slower DDR3.

The NVIDIA GeForce GT 745M is the better option for Vulkan-based workloads, leading by 22.5% in that specific test. Its memory subsystem is far superior: 64.00 GB/s of bandwidth versus 16.00 GB/s, on a 128-bit bus with GDDR5. It also has more shading units (384 vs. 320), more TMUs (32 vs. 20), and more ROPs (16 vs. 8). For users targeting modern Vulkan titles or memory-bandwidth-heavy rendering, the GT 745M’s architecture is more capable.

The overall database ranking reflects this: the Radeon R5 M320 sits at the 27th percentile of all GPUs, while the GT 745M sits at the 23rd. The AMD part’s higher average score (4657 vs. 3953) suggests slightly better all-around performance in the recorded tests, but the delta is modest. The GT 745M’s nearest rivals include the AMD Radeon R5 M420 (3956, delta -0.1%) and NVIDIA GeForce 830M (3957, delta -0.1%), while the Radeon M320’s closest competitor is the AMD Radeon RX 9060 XT 16 GB at exactly 4657 (delta 0%), with the NVIDIA Quadro P400 close behind at 4684 (delta -0.6%).

In practical terms, the Radeon R5 M320 should be selected if OpenCL compute or larger memory capacity is the priority. The GT 745M is preferable for Vulkan workloads and any situation where memory bandwidth matters more than raw shader throughput. Neither GPU is a clear overall winner; the two trade blows depending on the API and test.

Specification Differences

| Field | AMD Radeon R5 M320 | NVIDIA GeForce GT 745M |

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

| Architecture | GCN 1.0 | Kepler |

| Chip | Jet | GK107 |

| Process Node | 28 nm | 28 nm |

| Transistors | 690 million | 1,270 million |

| Die Size | 56 mm² | 118 mm² |

| Transistor Density | 12.3M / mm² | 10.8M / mm² |

| Base Clock | 780 MHz | Not listed |

| Boost Clock | 855 MHz | Not listed |

| Memory Clock | 1000 MHz, 2 Gbps effective | 1000 MHz, 4 Gbps effective |

| Memory Size | 4 GB | 2 GB |

| Memory Type | DDR3 | GDDR5 |

| Memory Bus Width | 64 bit | 128 bit |

| Memory Bandwidth | 16.00 GB/s | 64.00 GB/s |

| Shading Units | 320 | 384 |

| TMUs | 20 | 32 |

| ROPs | 8 | 16 |

| Pixel Rate | 6.840 GPixel/s | 4.392 GPixel/s |

| Texture Rate | 17.10 GTexel/s | 17.57 GTexel/s |

| FP32 | 547.2 GFLOPS | 421.6 GFLOPS |

| TDP | Not listed | 45 W |

| Bus Interface | PCIe 3.0 x8 | PCIe 3.0 x16 |

| DirectX | 12 (11_1) | 12 (11_0) |

| Vulkan | 1.2.170 | 1.2.175 |

| Release Date | 2015-05-04 | 2013-03-31 |

| Predecessor | Solar System | GeForce 600M |

| Successor | Polaris Mobile | GeForce 800M |

| Generation | Gem System (R5 M300) | GeForce 700M |

The most consequential differences are memory bandwidth (4x in favor of NVIDIA), shading resources (NVIDIA has more units), and FP32 throughput (AMD is about 30% higher). The AMD part’s higher pixel rate (6.840 GPixel/s vs. 4.392 GPixel/s) is notable given its lower ROP count, a result of its higher boost clock.

Head-to-Head Benchmarks

The recorded head-to-head data consists of two tests: Geekbench OpenCL and Geekbench Vulkan. The results are starkly divergent.

Geekbench OpenCL: AMD Radeon R5 M320 wins, 5051 vs. 3580. This is a 41.1% margin, the largest single-test gap in this comparison. The Radeon’s higher FP32 rate (547.2 GFLOPS) and higher pixel rate (6.840 GPixel/s) likely drive this advantage, as OpenCL workloads often scale with raw arithmetic throughput. The GT 745M’s lower FP32 (421.6 GFLOPS) and lower pixel rate (4.392 GPixel/s) put it at a clear disadvantage here, despite its superior memory bandwidth. In the database, the Radeon M320’s OpenCL score of 5051 is also its best recorded benchmark, while the GT 745M’s OpenCL result is its weakest at 3580.

Geekbench Vulkan: NVIDIA GeForce GT 745M wins, 5502 vs. 4262. The NVIDIA part leads by 22.5%. Vulkan workloads tend to be sensitive to memory bandwidth and memory subsystem efficiency, and the GT 745M’s 64.00 GB/s of GDDR5 bandwidth is four times the Radeon’s 16.00 GB/s. The GT 745M also has more TMUs (32 vs. 20) and ROPs (16 vs. 8), which can help with memory-bound rendering passes. Interestingly, the GT 745M’s Vulkan score of 5502 is its highest recorded benchmark, exceeding even its Metal score of 2777 and OpenCL score of 3580. The Radeon M320’s Vulkan score of 4262 is lower than its OpenCL result, suggesting its GCN 1.0 architecture is less optimized for Vulkan than Kepler.

Overall wins: The Radeon R5 M320 wins one test (OpenCL) and the GT 745M wins one test (Vulkan). The average benchmark scores follow the OpenCL trend: the Radeon averages 4657, the GT 745M averages 3953. That is an 18% gap in favor of AMD overall, driven almost entirely by the OpenCL blowout. The Vulkan result, however, shows the GT 745M is not obsolete; it remains competitive in the right API environment.

Context from nearest rivals: The Radeon M320’s average score of 4657 ties exactly with the AMD Radeon RX 9060 XT 16 GB (4657, delta 0%) and sits just below the NVIDIA Quadro P400 (4684, delta -0.6%) and just above the GeForce GTX 970M (4628, delta 0.6%). The GT 745M’s average of 3953 is nearly identical to the AMD Radeon R5 M420 (3956, delta -0.1%) and the NVIDIA GeForce 830M (3957, delta -0.1%). This places the two GPUs in different performance tiers in the database, with the Radeon M320 ranking higher overall, but the GT 745M’s Vulkan strength should not be discounted.

In summary, the benchmark data shows a GPU that wins on compute-heavy OpenCL (AMD) and a GPU that wins on modern graphics API Vulkan (NVIDIA). The choice depends entirely on the target workload.