AMD Radeon R7 M380 vs NVIDIA GeForce GTX 1660 Ti Comparison

AMD
RADEON

AMD Radeon R7 M380

CORE STATE Tropo
VRAM 4 GB
CLOCK SPEED 915 MHz
TDP —
BUS WIDTH 128 bit
ARCHITECTURE GCN 1.0
nm
PROCESS 28 nm
LAUNCH DATE 2015
VS
NVIDIA
GEFORCE

GeForce GTX 1660 Ti

CORE STATE TU116
VRAM 6 GB
CLOCK SPEED 1770 MHz
TDP 120 W
BUS WIDTH 192 bit
ARCHITECTURE Turing
nm
PROCESS 12 nm
LAUNCH DATE 2019

PERFORMANCE BENCHMARKS

geekbench_opencl
9,313
51,029
3dmark_3dmark_steel_nomad_dx12
N/A
1,061
geekbench_vulkan
N/A
5,827
passmark_directx_10
N/A
66
passmark_directx_11
N/A
103
passmark_directx_12
N/A
51
passmark_directx_9
N/A
190
passmark_g2d
N/A
804
passmark_g3d
N/A
12,871
passmark_gpu_compute
N/A
5,226

Analysis: AMD Radeon R7 M380 vs NVIDIA GeForce GTX 1660 Ti

FAQ

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

A: The AMD Radeon R7 M380 has an average benchmark score of 9,313, while the NVIDIA GeForce GTX 1660 Ti has an average score of 7,723. However, this average includes multiple tests for the NVIDIA card, while the AMD card has only one recorded benchmark.

Q: What is the key architectural difference between these two GPUs?

A: The AMD Radeon R7 M380 uses the GCN 1.0 architecture with a 28 nm process node, while the NVIDIA GeForce GTX 1660 Ti uses the Turing architecture on a 12 nm process node. The NVIDIA chip contains 6,600 million transistors versus 1,500 million for the AMD chip.

Q: How do their memory subsystems compare?

A: The AMD card has 4 GB of DDR3 memory on a 128-bit bus with 32.00 GB/s bandwidth. The NVIDIA card has 6 GB of GDDR6 memory on a 192-bit bus with 288.0 GB/s bandwidth. The NVIDIA memory operates at 12 Gbps effective, while the AMD memory runs at 2 Gbps effective.

Q: Which GPU scores higher in the Geekbench OpenCL benchmark?

A: The NVIDIA GeForce GTX 1660 Ti scores 51,029 compared to 9,313 for the AMD Radeon R7 M380. The NVIDIA card is 81.7% ahead in this test, which is the only head-to-head benchmark recorded in the database.

Q: What is the percentile ranking for each GPU against all GPUs in the database?

A: The AMD Radeon R7 M380 sits at the 46th percentile, while the NVIDIA GeForce GTX 1660 Ti is at the 41st percentile. Despite the NVIDIA card's higher raw performance in most tests, its average score is pulled down by lower results in some DirectX and compute benchmarks.

Q: What production status do both GPUs share?

A: Both the AMD Radeon R7 M380 and NVIDIA GeForce GTX 1660 Ti are marked as end-of-life products in the database, with release dates of May 2015 and February 2019, respectively.

Architecture Differences

The AMD Radeon R7 M380 is built on the GCN 1.0 architecture using the Tropo chip, manufactured by TSMC on a 28 nm process. The die measures 123 mm² and contains 1,500 million transistors, resulting in a transistor density of 12.2 million per square millimeter. This is an older generation design, part of the Gem System (R7 M300) family, with its predecessor listed as Solar System and successor as Polaris Mobile.

The NVIDIA GeForce GTX 1660 Ti uses the Turing architecture with the TU116 chip, also produced by TSMC but on a 12 nm process. The die size is 284 mm², housing 6,600 million transistors at a density of 23.2 million per square millimeter. It belongs to the GeForce 16 generation, succeeding the GeForce 10 series and preceding GeForce 20.

The process node difference is significant: 28 nm versus 12 nm, which explains the much higher transistor density in the NVIDIA chip. The NVIDIA card features 1,536 shading units, 96 texture mapping units, and 48 ROPs. The AMD card offers 640 shading units, 40 TMUs, and 16 ROPs. These resource counts directly influence the computed pixel and texture rates: the NVIDIA card reaches 84.96 GPixel/s and 169.9 GTexel/s, while the AMD card manages 14.64 GPixel/s and 36.60 GTexel/s.

Both cards support DirectX 12, OpenGL 4.6, and Vulkan, but the NVIDIA card supports DirectX 12 (12_1) and Vulkan 1.4, whereas the AMD card supports DirectX 12 (11_1) and Vulkan 1.2.170. The NVIDIA card also exposes FP16 compute at 10.87 TFLOPS (2:1 ratio), while the AMD card has no recorded FP16 capability. FP32 performance is 5.437 TFLOPS for NVIDIA versus 1,171.2 GFLOPS for AMD.

The NVIDIA card is a dual-slot design with a 1x 8-pin power connector and a suggested PSU of 300 W, with a TDP of 120 W. The AMD card has no recorded TDP, slot width, or power connector information. The NVIDIA card measures 229 mm in length, 111 mm in height, and 35 mm in width, while the AMD card has no recorded dimensions.

Head-to-Head Benchmarks

The only direct head-to-head benchmark in the database is Geekbench OpenCL. The NVIDIA GeForce GTX 1660 Ti scores 51,029, while the AMD Radeon R7 M380 scores 9,313. The delta is 81.7% in favor of NVIDIA, making this a decisive victory for the Turing-based card in compute workloads.

This result aligns with the raw specification differences. The NVIDIA card's FP32 throughput is 5.437 TFLOPS versus 1,171.2 GFLOPS for the AMD card, a factor of roughly 4.6 times. The memory bandwidth gap is even larger: 288.0 GB/s versus 32.00 GB/s, a 9x difference. These factors combine to produce the massive OpenCL score disparity.

However, the average benchmark score tells a more nuanced story. The NVIDIA card's average of 7,723 is lower than the AMD card's 9,313 because the NVIDIA card has additional benchmark results in the database. Its Passmark G3D score is 12,871, but its Passmark DirectX 9 score is only 190, and DirectX 10 is 66. The Passmark G2D score is 804, and GPU compute is 5,226. The 3DMark Steel Nomad DX12 score is 1,061, and Geekbench Vulkan is 5,827.

The AMD card has only one benchmark, Geekbench OpenCL at 9,313, which sets its average and percentile. The nearest rivals to the AMD card are all within 1%: the NVIDIA GeForce GTX 850M at 9,302 (0.1% delta), GeForce GTX 465 at 9,294 (0.2%), GeForce GTX 960 at 9,273 (0.4%), and AMD Radeon Vega 8 at 9,221 (1%). This indicates the AMD card sits in a tight performance cluster around the 9,300 mark.

The NVIDIA card's nearest rivals are also tightly grouped: AMD Radeon 540 at 7,673 (0.7% delta), Radeon Pro WX 3100 at 7,580 (1.9%), Radeon R7 250 at 7,557 (2.2%), and Intel Arc A310 at 7,550 (2.3%). The NVIDIA card's average is pulled down by its lower DirectX scores, which are outliers compared to its strong OpenCL and G3D results.

In the single head-to-head test, the NVIDIA card wins decisively. The benchmark data shows an 81.7% lead in OpenCL compute, which is the only test where both cards appear together in the database.

Specification Differences

The two GPUs differ across nearly every recorded specification field. The process node differs: 28 nm for AMD versus 12 nm for NVIDIA. Transistor count is 1,500 million versus 6,600 million, and die size is 123 mm² versus 284 mm², resulting in transistor densities of 12.2M/mm² versus 23.2M/mm².

Clock speeds differ substantially. The AMD card has a base clock of 900 MHz and a boost of 915 MHz, with memory at 1000 MHz (2 Gbps effective). The NVIDIA card has a base of 1500 MHz and a boost of 1770 MHz, with memory at 1500 MHz (12 Gbps effective).

Memory configuration is another major divider: 4 GB DDR3 on a 128-bit bus with 32.00 GB/s bandwidth for AMD, versus 6 GB GDDR6 on a 192-bit bus with 288.0 GB/s bandwidth for NVIDIA.

Compute resources: 640 shading units, 40 TMUs, and 16 ROPs for AMD; 1,536 shading units, 96 TMUs, and 48 ROPs for NVIDIA. Pixel rate is 14.64 GPixel/s versus 84.96 GPixel/s, and texture rate is 36.60 GTexel/s versus 169.9 GTexel/s. FP32 is 1,171.2 GFLOPS versus 5.437 TFLOPS.

The NVIDIA card has a TDP of 120 W, is dual-slot, uses 1x 8-pin power, and suggests a 300 W PSU. The AMD card has none of these recorded. Display outputs are listed for NVIDIA (1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a) but not for AMD. The NVIDIA card has dimensions (229 mm length, 111 mm height, 35 mm width), while AMD has none.

API support differs: DirectX 12 (11_1) for AMD versus DirectX 12 (12_1) for NVIDIA, and Vulkan 1.2.170 versus 1.4. The NVIDIA card also has FP16 at 10.87 TFLOPS (2:1), while AMD has no FP16 data.

Release dates differ by nearly four years: May 2015 for AMD versus February 2019 for NVIDIA. The NVIDIA card has a recorded launch MSRP of 279 USD.

The Verdict

The benchmark data clearly favors the NVIDIA GeForce GTX 1660 Ti in raw compute performance. The OpenCL head-to-head shows an 81.7% advantage, and the NVIDIA card's FP32 throughput is over four times higher. For any workload that stresses compute or memory bandwidth, the NVIDIA card is the superior choice based on the recorded measurements.

The AMD Radeon R7 M380 does hold a higher average benchmark score (9,313 versus 7,723) and a higher percentile ranking (46th versus 41st). This is because the NVIDIA card's average is diluted by its weaker Passmark DirectX 9, 10, and 12 scores, which are not present in the AMD card's single benchmark. Users who prioritize OpenCL compute should look at the NVIDIA card's 51,029 score, while those who value a consistent single-metric profile might note the AMD card's simpler benchmark record.

The architecture gap is generational. The NVIDIA card uses a 12 nm Turing design with 6,600 million transistors, while the AMD card uses a 28 nm GCN 1.0 design with 1,500 million. The NVIDIA card offers GDDR6 memory with 288.0 GB/s bandwidth, 6 GB capacity, and a 192-bit bus. The AMD card provides DDR3 at 32.00 GB/s, 4 GB capacity, and a 128-bit bus. These are not comparable memory systems.

For gaming or general GPU compute, the data points to the NVIDIA GeForce GTX 1660 Ti as the stronger performer. Its Passmark G3D score of 12,871 and 3DMark Steel Nomad DX12 score of 1,061, combined with the OpenCL result, indicate a well-rounded modern GPU. The AMD card's single benchmark does not demonstrate capability beyond the 9,313 OpenCL score, which is matched by several older NVIDIA parts within 1%.

The NVIDIA card's nearest rivals in the database are all AMD and Intel parts within 2.3%, including the Radeon 540 and Intel Arc A310. This suggests the NVIDIA card's average score is representative of a lower-tier modern GPU, despite its strong OpenCL performance. The AMD card's nearest rivals are all NVIDIA parts from earlier generations, indicating it competes in a different performance class.

The verdict from the data: the NVIDIA GeForce GTX 1660 Ti is the choice for users needing high compute throughput, modern API support, and substantial memory bandwidth. The AMD Radeon R7 M380 is a legacy part with a higher average score in this database due to fewer benchmarks, but its specifications and single test result place it in a much lower performance tier. The NVIDIA card wins the only direct comparison, and its full benchmark suite shows capability across multiple workloads. The AMD card's data is too limited to recommend for any specific task beyond the 9,313 OpenCL score it recorded.

DETAILED SPECIFICATIONS

SPECIFICATION
R7 M380
GTX 1660 Ti
Core Specs
Shading Units
640
1,536 +140.0%
Shaders
640
1,536 +140.0%
TMUs
40
96 +140.0%
ROPs
16
48 +200.0%
Compute Units
10
—
SM Count
—
24
Clocks
Base Clock
900 MHz
1500 MHz
Boost Clock
915 MHz
1770 MHz
Memory Clock
1000 MHz 2 Gbps effective
1500 MHz 12 Gbps effective
Memory
Memory Size
4 GB
6 GB
VRAM (MB)
4,096
6,144 +50.0%
Memory Type
DDR3
GDDR6
Memory Bus
128 bit
192 bit
Bandwidth
32.00 GB/s
288.0 GB/s
Cache
L1 Cache
16 KB (per CU)
64 KB (per SM)
L2 Cache
256 KB
1536 KB
Performance
Pixel Rate
14.64 GPixel/s
84.96 GPixel/s
Texture Rate
36.60 GTexel/s
169.9 GTexel/s
FP32 (TFLOPS)
1,171.2 GFLOPS
5.437 TFLOPS
FP64 (TFLOPS)
73.20 GFLOPS (1:16)
169.9 GFLOPS (1:32)
FP16 (TFLOPS)
—
10.87 TFLOPS (2:1)
Power
TDP
—
120 W
TDP (W)
—
120
Suggested PSU
—
300 W
Power Connectors
—
1x 8-pin
Architecture
Architecture
GCN 1.0
Turing
GPU Name
Tropo
TU116
Generation
Gem System (R7 M300)
GeForce 16
Process Size
28 nm
12 nm
Transistors
1,500 million
6,600 million
Die Size
123 mm²
284 mm²
Foundry
TSMC
TSMC
Density
12.2M / mm²
23.2M / mm²
API Support
DirectX
12 (11_1)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.2.170
1.4
OpenCL
2.1 (1.2)
3.0
CUDA
—
7.5
Shader Model
6.5 (5.1)
6.8
Physical
Slot Width
—
Dual-slot
Length
—
229 mm 9 inches
Height
—
111 mm 4.4 inches
Outputs
—
1x DVI1x HDMI 2.01x DisplayPort 1.4a
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Launch Price
—
279 USD
Production
End-of-life
End-of-life
Predecessor
Solar System
GeForce 10
Successor
Polaris Mobile
GeForce 20
View Radeon R7 M380 Details View GeForce GTX 1660 Ti Details