AMD Radeon RX 590 vs NVIDIA GeForce GTX 1060 6 GB Comparison

AMD
RADEON

AMD Radeon RX 590

CORE STATE Polaris 30
VRAM 8 GB
CLOCK SPEED 1545 MHz
TDP 175 W
BUS WIDTH 256 bit
ARCHITECTURE GCN 4.0
nm
PROCESS 12 nm
LAUNCH DATE 2018
VS
NVIDIA
GEFORCE

GeForce GTX 1060 6 GB

CORE STATE GP106
VRAM 6 GB
CLOCK SPEED 1709 MHz
TDP 120 W
BUS WIDTH 192 bit
ARCHITECTURE Pascal
nm
PROCESS 16 nm
LAUNCH DATE 2016

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
1,081
N/A
geekbench_metal
48,407
14,587
geekbench_opencl
N/A
32,322
geekbench_vulkan
N/A
18,659

Analysis: AMD Radeon RX 590 vs NVIDIA GeForce GTX 1060 6 GB

Head-to-Head Benchmarks

The recorded database contains a single direct head-to-head benchmark between the AMD Radeon RX 590 and the NVIDIA GeForce GTX 1060 6 GB: the Geekbench Metal test. The results are decisively in favor of the AMD card. The RX 590 scores 48,407 points, while the GTX 1060 6 GB scores 14,587 points. This represents a 231.9% advantage for the AMD Radeon RX 590.

This is a massive margin, and it is worth contextualizing. The Geekbench Metal test is a compute-oriented workload that heavily leverages the shading units and memory subsystem. The RX 590's 48,407 score is more than three times the GTX 1060's result. The delta of 231.9% is not a small incremental gain; it indicates that in this specific API and workload, the RX 590 is in a completely different performance class. The GTX 1060 6 GB does not win any of the recorded head-to-head benchmarks, as the data shows a single win for the RX 590 and zero for the GTX 1060.

Looking at the broader average benchmark scores from the database, the two cards are closer than the Metal test suggests. The RX 590 has an average benchmark score of 24,744 across all recorded tests, whereas the GTX 1060 6 GB averages 21,856. That is a difference of roughly 13% in favor of the AMD part, a much narrower gap than the 231.9% seen in the Metal test. The average score is a more balanced view across various synthetic workloads, and it shows the RX 590 maintaining a clear but less dramatic lead.

The percentile rankings reinforce this picture. The RX 590 sits at the 70th percentile among all GPUs in the database, while the GTX 1060 6 GB sits at the 67th percentile. Both are mid-range performers historically, but the RX 590 ranks slightly higher. The nearest rivals for each card also help calibrate expectations. The RX 590's nearest competitor by average score is the NVIDIA RTX A5000 Mobile, which scores 24,763, just 0.1% higher than the RX 590's 24,744. On the other side, the GTX 1060 6 GB's closest rival is the NVIDIA Quadro RTX 5000, which scores 21,629, about 1% below the GTX 1060's 21,856. The RX 590 also edges out the Intel Arc A350M (24,647, 0.4% lower) and the AMD Radeon RX 6600 XT (24,442, 1.2% lower), while the GTX 1060 sits ahead of the AMD Radeon RX 6700S (22,154, 1.3% higher) and the AMD Radeon RX 5700 (22,170, 1.4% higher). The relative positions are consistent: the RX 590 is a step above the GTX 1060 in aggregate performance.

Architecture Differences

The architectural divide between these two cards is substantial. The AMD Radeon RX 590 is built on the Polaris 30 chip, using the GCN 4.0 architecture, and it is fabricated on a 12 nm process at GlobalFoundries. The NVIDIA GeForce GTX 1060 6 GB uses the GP106 chip, based on the Pascal architecture, and is manufactured on a 16 nm process at TSMC. The process node difference gives AMD a manufacturing advantage in terms of transistor density: the RX 590 packs 5,700 million transistors into a 232 mm² die, yielding a density of 24.6 million transistors per square millimeter. The GTX 1060 has 4,400 million transistors on a 200 mm² die, for a density of 22.0 million per square millimeter.

The compute resources differ sharply. The RX 590 has 2,304 shading units, 144 texture mapping units, and 32 raster operation pipelines. The GTX 1060 6 GB has 1,280 shading units, 80 TMUs, and 48 ROPs. So while the AMD card has far more shaders and texture units, the NVIDIA card has 50% more ROPs. This explains the rasterization throughput numbers: the GTX 1060 achieves a pixel rate of 82.03 GPixel/s, while the RX 590 manages 49.44 GPixel/s. In contrast, the RX 590's texture rate is 222.5 GTexel/s versus the GTX 1060's 136.7 GTexel/s. The FP32 compute figures follow the shading unit counts: the RX 590 delivers 7.119 TFLOPS, while the GTX 1060 delivers 4.375 TFLOPS. The FP16 data is even more divergent. The RX 590 runs FP16 at a 1:1 ratio, matching its FP32 throughput at 7.119 TFLOPS. The GTX 1060's FP16 is severely cut down, running at just 68.36 GFLOPS, a 1:64 ratio, which is roughly 1% of the RX 590's FP16 capability.

Memory configurations also differ. The RX 590 has 8 GB of GDDR5 on a 256-bit bus, producing 256.0 GB/s of bandwidth. The GTX 1060 6 GB has 6 GB of GDDR5 on a 192-bit bus, producing 192.2 GB/s. Clock speeds are comparable at the base and boost levels: the RX 590 runs at 1469 MHz base and 1545 MHz boost, while the GTX 1060 runs at 1506 MHz base and 1709 MHz boost. The NVIDIA card actually has higher clocks, but it has fewer cores, so the aggregate throughput still favors AMD. Both cards support PCIe 3.0 x16 and have dual-slot designs. The RX 590 requires a 1x 8-pin power connector and a 450 W suggested PSU, while the GTX 1060 requires a 1x 6-pin connector and a 300 W suggested PSU. The TDP figures reflect this: 175 W for the RX 590 versus 120 W for the GTX 1060.

API support shows a notable difference in DirectX feature level. The RX 590 supports DirectX 12 at feature level 12_0, while the GTX 1060 supports 12_1. For Vulkan, the GTX 1060 supports version 1.4, while the RX 590 supports 1.3. OpenGL support is identical at 4.6. Neither card has dedicated ray tracing or tensor cores, as those features are absent from both specifications.

Where Each One Wins

The AMD Radeon RX 590 is the clear winner in compute-heavy workloads, particularly those that stress FP32 or FP16 throughput. Its 7.119 TFLOPS FP32 and 1:1 FP16 ratio give it a massive advantage in any application that can use these paths. The Geekbench Metal result, where it leads by 231.9%, is a direct demonstration of this. The RX 590 also wins on memory bandwidth: 256.0 GB/s versus 192.2 GB/s, and it has 8 GB of VRAM versus 6 GB. For modern games or applications that exceed 6 GB of video memory, the RX 590 has a clear capacity advantage. Its texture rate of 222.5 GTexel/s is also significantly higher, which benefits games with heavy texture filtering.

The NVIDIA GeForce GTX 1060 6 GB wins on rasterization throughput. Its pixel rate of 82.03 GPixel/s is nearly double the RX 590's 49.44 GPixel/s, and its 48 ROPs outnumber the RX 590's 32. This suggests that in fill-rate-limited scenarios, such as high-resolution rendering with simple shaders, the GTX 1060 could hold its own or even pull ahead. The GTX 1060 also has higher boost clocks (1709 MHz versus 1545 MHz) and a lower TDP of 120 W versus 175 W, making it a more power-efficient option. The lower power draw also means a lower suggested PSU rating: 300 W versus 450 W.

The RX 590's average benchmark score of 24,744 places it ahead of the GTX 1060's 21,856, so in the aggregate, the AMD card is the stronger performer. However, the GTX 1060's 67th percentile ranking versus the RX 590's 70th shows that both cards are within the same general tier of historical mid-range GPUs. For users who prioritize compute, texture throughput, VRAM capacity, or FP16 capability, the RX 590 is the obvious choice. For users who prioritize pixel fill rate, power efficiency, or a lower PSU requirement, the GTX 1060 has specific advantages. The GTX 1060 also supports DirectX 12_1, a higher feature level than the RX 590's 12_0, and newer Vulkan 1.4 support, which could matter for specific titles or API features.

FAQ

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

A: The AMD Radeon RX 590 has an average benchmark score of 24,744, while the NVIDIA GeForce GTX 1060 6 GB has an average of 21,856, a difference of roughly 13% in favor of the RX 590.

Q: How big is the difference in the Geekbench Metal test?

A: The RX 590 scores 48,407, and the GTX 1060 scores 14,587, giving the RX 590 a 231.9% lead in that specific benchmark.

Q: Does the GTX 1060 6 GB have any advantages in memory capacity?

A: No, the RX 590 has 8 GB of GDDR5, while the GTX 1060 has 6 GB. The RX 590 also has a wider 256-bit bus and higher bandwidth at 256.0 GB/s versus 192.2 GB/s.

Q: What is the TDP difference between the two cards?

A: The RX 590 has a TDP of 175 W, and the GTX 1060 has a TDP of 120 W. The suggested PSU ratings are 450 W and 300 W, respectively.

Q: Which card has more shading units?

A: The RX 590 has 2,304 shading units, while the GTX 1060 has 1,280. The RX 590 also has 144 TMUs versus 80, but the GTX 1060 has more ROPs, 48 versus 32.

Q: Do these cards support ray tracing or tensor cores?

A: No, neither the RX 590 nor the GTX 1060 includes RT cores or tensor cores in their specifications.

Specification Differences

Process Node: The AMD Radeon RX 590 is built on a 12 nm process at GlobalFoundries, while the NVIDIA GeForce GTX 1060 6 GB uses a 16 nm process at TSMC.

Transistors and Die Size: The RX 590 has 5,700 million transistors on a 232 mm² die (24.6M per mm²), while the GTX 1060 has 4,400 million on a 200 mm² die (22.0M per mm²).

Shading Units: 2,304 on the RX 590 versus 1,280 on the GTX 1060.

TMUs: 144 on the RX 590 versus 80 on the GTX 1060.

ROPs: 32 on the RX 590 versus 48 on the GTX 1060.

Base Clock: 1469 MHz on the RX 590 versus 1506 MHz on the GTX 1060.

Boost Clock: 1545 MHz on the RX 590 versus 1709 MHz on the GTX 1060.

Memory Size: 8 GB on the RX 590 versus 6 GB on the GTX 1060.

Memory Bus Width: 256 bit on the RX 590 versus 192 bit on the GTX 1060.

Memory Bandwidth: 256.0 GB/s on the RX 590 versus 192.2 GB/s on the GTX 1060.

Pixel Rate: 49.44 GPixel/s on the RX 590 versus 82.03 GPixel/s on the GTX 1060.

Texture Rate: 222.5 GTexel/s on the RX 590 versus 136.7 GTexel/s on the GTX 1060.

FP32 Compute: 7.119 TFLOPS on the RX 590 versus 4.375 TFLOPS on the GTX 1060.

FP16 Compute: 7.119 TFLOPS (1:1) on the RX 590 versus 68.36 GFLOPS (1:64) on the GTX 1060.

TDP: 175 W on the RX 590 versus 120 W on the GTX 1060.

Power Connectors: 1x 8-pin on the RX 590 versus 1x 6-pin on the GTX 1060.

Suggested PSU: 450 W on the RX 590 versus 300 W on the GTX 1060.

Display Outputs: The RX 590 has 1x HDMI 2.0b and 3x DisplayPort 1.4a, while the GTX 1060 has 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a.

DirectX Support: The RX 590 supports DirectX 12 (12_0), while the GTX 1060 supports DirectX 12 (12_1).

Vulkan Support: The RX 590 supports Vulkan 1.3, while the GTX 1060 supports Vulkan 1.4.

Dimensions: The RX 590 is 241 mm (9.5 inches) long, while the GTX 1060 is 250 mm (9.8 inches) long and 111 mm (4.4 inches) tall.

Release Date: The RX 590 was released on 2018-11-14, while the GTX 1060 was released on 2016-07-18.

Launch MSRP: The RX 590 had a launch MSRP of 279 USD, while the GTX 1060 had a launch MSRP of 299 USD.

Percentile Ranking: The RX 590 ranks at the 70th percentile among all GPUs, while the GTX 1060 ranks at the 67th percentile.

Average Benchmark Score: The RX 590 averages 24,744, while the GTX 1060 averages 21,856.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 590
GTX 1060 6 GB
Core Specs
Shading Units
2,304
1,280 -44.4%
Shaders
2,304
1,280 -44.4%
TMUs
144
80 -44.4%
ROPs
32
48 +50.0%
Compute Units
36
—
SM Count
—
10
Clocks
Base Clock
1469 MHz
1506 MHz
Boost Clock
1545 MHz
1709 MHz
Memory Clock
2000 MHz 8 Gbps effective
2002 MHz 8 Gbps effective
Memory
Memory Size
8 GB
6 GB
VRAM (MB)
8,192
6,144 -25.0%
Memory Type
GDDR5
GDDR5
Memory Bus
256 bit
192 bit
Bandwidth
256.0 GB/s
192.2 GB/s
Cache
L1 Cache
16 KB (per CU)
48 KB (per SM)
L2 Cache
2 MB
1536 KB
Performance
Pixel Rate
49.44 GPixel/s
82.03 GPixel/s
Texture Rate
222.5 GTexel/s
136.7 GTexel/s
FP32 (TFLOPS)
7.119 TFLOPS
4.375 TFLOPS
FP64 (TFLOPS)
445.0 GFLOPS (1:16)
136.7 GFLOPS (1:32)
FP16 (TFLOPS)
7.119 TFLOPS (1:1)
68.36 GFLOPS (1:64)
Power
TDP
175 W
120 W
TDP (W)
175
120 -31.4%
Suggested PSU
450 W
300 W
Power Connectors
1x 8-pin
1x 6-pin
Architecture
Architecture
GCN 4.0
Pascal
GPU Name
Polaris 30
GP106
Generation
Polaris (RX 500)
GeForce 10
Process Size
12 nm
16 nm
Transistors
5,700 million
4,400 million
Die Size
232 mm²
200 mm²
Foundry
GlobalFoundries
TSMC
Density
24.6M / mm²
22.0M / mm²
API Support
DirectX
12 (12_0)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.3
1.4
OpenCL
2.1
3.0
CUDA
—
6.1
Shader Model
6.7
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
241 mm 9.5 inches
250 mm 9.8 inches
Height
—
111 mm 4.4 inches
Outputs
1x HDMI 2.0b3x DisplayPort 1.4a
1x DVI1x HDMI 2.03x DisplayPort 1.4a
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Launch Price
279 USD
299 USD
Production
End-of-life
End-of-life
Predecessor
Arctic Islands
GeForce 900
Successor
Vega
GeForce 20
View Radeon RX 590 Details View GeForce GTX 1060 6 GB Details