AMD Radeon R7 M370 vs NVIDIA GeForce GTX 1660 Ti Comparison

The Verdict

The comparison between the NVIDIA GeForce GTX 1660 Ti and the AMD Radeon R7 M370 is not a contest of equals; it is a generational and architectural mismatch. The data shows the GTX 1660 Ti is the clear choice for anyone needing serious compute or modern graphics performance. Its average benchmark score of 7723 places it in the 41st percentile of all GPUs, while the R7 M370 averages 6764, sitting in the 38th percentile. That gap of roughly 14% in average score understates the real-world difference in demanding workloads, where the NVIDIA card's lead becomes enormous.

The GTX 1660 Ti is for the builder who wants a capable, end-of-life card that still handles modern DirectX 12 titles and compute tasks. It has a launch MSRP of 279 USD, and while it is no longer in production, its specifications remain relevant for 1080p gaming and general GPU compute. The R7 M370, also end-of-life, is a legacy mobile-oriented part from 2015. It should only be considered if the workload is extremely light, such as basic desktop acceleration or older APIs, and even then its Vulkan score is the only area where it beats the newer card.

If the task is anything beyond casual, the GTX 1660 Ti wins outright. For a user constrained to an older system that only needs a low-power display adapter, the R7 M370 might suffice, but benchmark results indicate it is outclassed in every compute-heavy scenario. The verdict is straightforward: pick the GTX 1660 Ti for performance, pick the R7 M370 only if the system cannot physically or electrically accommodate the NVIDIA card.

Architecture Differences

The two GPUs come from different eras and design philosophies. The NVIDIA GeForce GTX 1660 Ti uses the TU116 chip built on Turing architecture, fabricated on a 12 nm process at TSMC. It packs 6,600 million transistors into a 284 mm² die, giving a transistor density of 23.2M per mm². The AMD Radeon R7 M370 uses the Litho chip based on GCN 1.0 architecture, also made by TSMC, but on a much older 28 nm process. It contains only 950 million transistors on a 77 mm² die, with a density of 12.3M per mm². That process gap alone explains a large portion of the performance difference.

Core counts reinforce the divide. The GTX 1660 Ti has 1,536 shading units, 96 texture mapping units, and 48 ROPs. The R7 M370 has 384 shading units, 24 TMUs, and just 8 ROPs. In raw math throughput, the NVIDIA card delivers 5.437 TFLOPS of FP32 compute, while the AMD card manages 737.3 GFLOPS. The GTX 1660 Ti also supports FP16 at 10.87 TFLOPS with a 2:1 ratio, a feature the R7 M370 lacks entirely. Neither card has ray tracing or tensor cores, so that is not a differentiator.

Memory architecture is another major split. The GTX 1660 Ti uses 6 GB of GDDR6 on a 192-bit bus, yielding 288.0 GB/s of bandwidth and a memory clock of 1500 MHz (12 Gbps effective). The R7 M370 uses 2 GB of GDDR5 on a 128-bit bus, with 57.60 GB/s of bandwidth and a 900 MHz memory clock (3.6 Gbps effective). The NVIDIA card has nearly five times the memory bandwidth, which matters greatly in texture-heavy scenes and compute workloads.

API support also differs. The GTX 1660 Ti supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The R7 M370 supports DirectX 12 (11_1), OpenGL 4.6, and Vulkan 1.2.170. The newer Vulkan version on the NVIDIA card is a practical advantage for modern titles. The bus interface also differs: the GTX 1660 Ti uses PCIe 3.0 x16, while the R7 M370 uses PCIe 3.0 x8, halving the available bandwidth to the host system.

The GTX 1660 Ti has a 120 W TDP, a dual-slot cooler, and requires a single 8-pin power connector with a 300 W suggested PSU. The R7 M370 has no recorded TDP, slot width, power connectors, or PSU recommendation in the database, which reflects its mobile-oriented design. The NVIDIA card is 229 mm (9 inches) long, 111 mm (4.4 inches) tall, and 35 mm (1.4 inches) wide, while the AMD card has no recorded physical dimensions.

FAQ

Q: Which card has the higher average benchmark score?

A: The NVIDIA GeForce GTX 1660 Ti averages 7723, while the AMD Radeon R7 M370 averages 6764. The GTX 1660 Ti sits in the 41st percentile of all GPUs, the R7 M370 in the 38th percentile.

Q: Is the GTX 1660 Ti ahead in Geekbench OpenCL?

A: Yes, by a massive margin. The GTX 1660 Ti scores 51029 in geekbench_opencl, the R7 M370 scores 7063. That is a 622.5% delta in favor of NVIDIA.

Q: Does the R7 M370 win any benchmark at all?

A: Yes, it wins geekbench_vulkan. There the R7 M370 scores 6465, the GTX 1660 Ti scores 5827, a 9.9% lead for AMD. That is the only head-to-head test it wins, giving it 1 win versus the GTX 1660 Ti's 1 win.

Q: How do their nearest rivals compare to the GTX 1660 Ti?

A: The GTX 1660 Ti's closest rivals by average score are the AMD Radeon 540 (7673, 0.7% behind), AMD Radeon Pro WX 3100 (7580, 1.9% behind), AMD Radeon R7 250 (7557, 2.2% behind), and Intel Arc A310 (7550, 2.3% behind). The R7 M370's nearest rivals are the AMD FirePro M5100 (6830, 1% ahead), NVIDIA GeForce GT 1010 (6698, 1% behind), AMD Radeon R7 M460 (6612, 2.3% behind), and NVIDIA GeForce GTX 675M (6946, 2.6% ahead).

Q: What is the memory configuration difference?

A: The GTX 1660 Ti has 6 GB of GDDR6 on a 192-bit bus with 288.0 GB/s bandwidth. The R7 M370 has 2 GB of GDDR5 on a 128-bit bus with 57.60 GB/s bandwidth.

Q: Which card has better API support?

A: The GTX 1660 Ti supports DirectX 12 (12_1) and Vulkan 1.4, while the R7 M370 supports DirectX 12 (11_1) and Vulkan 1.2.170. Both support OpenGL 4.6.

Specification Differences

| Specification | NVIDIA GeForce GTX 1660 Ti | AMD Radeon R7 M370 |

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

| Architecture | Turing | GCN 1.0 |

| Process Node | 12 nm | 28 nm |

| Transistors | 6,600 million | 950 million |

| Die Size | 284 mm² | 77 mm² |

| Transistor Density | 23.2M / mm² | 12.3M / mm² |

| Base Clock | 1500 MHz | 875 MHz |

| Boost Clock | 1770 MHz | 960 MHz |

| Memory Clock | 1500 MHz (12 Gbps effective) | 900 MHz (3.6 Gbps effective) |

| Memory Size | 6 GB | 2 GB |

| Memory Type | GDDR6 | GDDR5 |

| Memory Bus Width | 192 bit | 128 bit |

| Memory Bandwidth | 288.0 GB/s | 57.60 GB/s |

| Shading Units | 1536 | 384 |

| TMUs | 96 | 24 |

| ROPs | 48 | 8 |

| Pixel Rate | 84.96 GPixel/s | 7.680 GPixel/s |

| Texture Rate | 169.9 GTexel/s | 23.04 GTexel/s |

| FP32 | 5.437 TFLOPS | 737.3 GFLOPS |

| FP16 | 10.87 TFLOPS (2:1) | null |

| TDP | 120 W | null |

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

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

| Vulkan | 1.4 | 1.2.170 |

| Display Outputs | 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a | null |

| Power Connectors | 1x 8-pin | null |

| Suggested PSU | 300 W | null |

| Slot Width | Dual-slot | null |

| Dimensions | 229 mm x 111 mm x 35 mm | null |

Head-to-Head Benchmarks

The database records only two common benchmarks between these cards, and the results are starkly lopsided in compute but surprisingly competitive in one API.

In geekbench_opencl, the GTX 1660 Ti scores 51029 against the R7 M370's 7063. That is a 622.5% delta, meaning the NVIDIA card delivers over seven times the OpenCL compute performance. This is the single biggest win in the comparison and reflects the combined effect of more shading units, higher clocks, and vastly more memory bandwidth. Any workload that uses OpenCL, such as video encoding, physics simulation, or GPGPU tasks, will be dramatically faster on the GTX 1660 Ti.

In geekbench_vulkan, the tables turn. The R7 M370 scores 6465, while the GTX 1660 Ti scores 5827. That is a 9.9% delta in favor of AMD. This is an unusual result, given the NVIDIA card's superior hardware, but the recorded data stands. The Vulkan score may reflect driver maturity or specific workload characteristics in the test. Still, it shows that the R7 M370 is not entirely without merit in modern low-level APIs.

The win count is 1-1, but the magnitude of the OpenCL victory dwarfs the Vulkan one. A 622.5% advantage is far more significant than a 9.9% advantage. The GTX 1660 Ti's average benchmark score of 7723 versus 6764 for the R7 M370 confirms that overall, the NVIDIA card is the stronger performer. The Vulkan win for AMD is a narrow outlier, not a trend.

Where Each One Wins

The GTX 1660 Ti wins in every compute-heavy scenario. Its OpenCL score of 51029 versus 7063 means tasks like rendering, scientific computation, machine learning inference, and video processing will be seven times faster. The 5.437 TFLOPS of FP32 compute, 169.9 GTexel/s texture rate, and 84.96 GPixel/s pixel rate make it suitable for modern gaming at 1080p with high settings. The 6 GB of GDDR6 memory with 288.0 GB/s bandwidth handles large textures and high-resolution assets without bottlenecking. Its DirectX 12 (12_1) support and Vulkan 1.4 compatibility ensure it can run current and near-future titles. The 120 W TDP, dual-slot cooler, and 1x 8-pin power connector mean it fits into standard desktop builds with a 300 W PSU. Its 229 mm length and 35 mm width require a case with reasonable clearance, but that is a minor constraint.

The R7 M370 wins only in the Vulkan benchmark, where it scores 6465 against 5827, a 9.9% edge. That is a narrow victory and one that does not translate into broader superiority. Its 737.3 GFLOPS of FP32 compute, 23.04 GTexel/s texture rate, and 7.680 GPixel/s pixel rate are sufficient for basic desktop acceleration, older DirectX 11 titles, or light 2D workloads. The 2 GB of GDDR5 memory on a 128-bit bus with 57.60 GB/s bandwidth is enough for low-resolution textures and simple scenes. Its PCIe 3.0 x8 interface and lack of recorded power connectors suggest it was designed for laptops or low-power systems. The 28 nm process and GCN 1.0 architecture are dated, and the 950 million transistor count is a fraction of the NVIDIA card's 6,600 million.

For a practical builder, the choice is clear. The GTX 1660 Ti is a desktop-oriented card with a measurable performance advantage in compute and a massive lead in memory bandwidth. The R7 M370 is a legacy part that only makes sense in a system that cannot take a dual-slot, 229 mm, 120 W card with a single 8-pin connector. If the system can physically and electrically support the NVIDIA card, the data says take it. If not, the R7 M370 can handle basic tasks, but expect it to struggle with anything demanding. The Vulkan win is real but small, and it does not offset the 622.5% OpenCL deficit. The GTX 1660 Ti is the card to buy for performance; the R7 M370 is the card to use only when no other option fits.