NVIDIA GeForce GTX 1060 3 GB vs NVIDIA GeForce RTX 2070 SUPER Comparison

NVIDIA
GEFORCE

NVIDIA GeForce GTX 1060 3 GB

CORE STATE GP106
VRAM 3 GB
CLOCK SPEED 1708 MHz
TDP 120 W
BUS WIDTH 192 bit
ARCHITECTURE Pascal
nm
PROCESS 16 nm
LAUNCH DATE 2016
VS
NVIDIA
GEFORCE

GeForce RTX 2070 SUPER

CORE STATE TU104
VRAM 8 GB
CLOCK SPEED 1770 MHz
TDP 215 W
BUS WIDTH 256 bit
ARCHITECTURE Turing
nm
PROCESS 12 nm
LAUNCH DATE 2019

PERFORMANCE BENCHMARKS

geekbench_metal
13,527
N/A
geekbench_opencl
27,001
83,358
geekbench_vulkan
17,475
90,637
3dmark_3dmark_steel_nomad_dx12
N/A
1,651
passmark_directx_10
N/A
132
passmark_directx_11
N/A
151
passmark_directx_12
N/A
67
passmark_directx_9
N/A
223
passmark_g2d
N/A
878
passmark_g3d
N/A
18,169
passmark_gpu_compute
N/A
7,557

Analysis: NVIDIA GeForce GTX 1060 3 GB vs NVIDIA GeForce RTX 2070 SUPER

NVIDIA GeForce RTX 2070 SUPER vs NVIDIA GeForce GTX 1060 3 GB: the data shows a generational chasm between two end-of-life graphics cards. The RTX 2070 SUPER, a Turing-based part from the GeForce 20-series, holds an overwhelming lead in the limited head-to-head benchmark set, while the GTX 1060 3 GB, a Pascal-based GeForce 10-series card, remains a capable legacy performer. The average benchmark scores—20282 for the RTX 2070 SUPER versus 19334 for the GTX 1060 3 GB—favor the newer card by roughly 5%, but the individual compute tests reveal a far larger gap that is defined by architecture and memory configuration.

Head-to-Head Benchmarks

The most decisive victory for the RTX 2070 SUPER comes in the Geekbench Vulkan test, where it scores 90637 against the GTX 1060 3 GB's 17475. That is a delta of 418.7%, meaning the RTX 2070 SUPER delivers more than five times the Vulkan performance of the older card. This is not a marginal improvement; it represents a fundamental shift in capability, driven by the newer architecture's support for modern API features and a substantially wider memory bus.

In the Geekbench OpenCL test, the RTX 2070 SUPER again dominates, scoring 83358 versus 27001 for the GTX 1060 3 GB. The delta here is 208.7%, a threefold advantage in raw compute throughput. This aligns with the FP32 performance figures: the RTX 2070 SUPER is rated at 9.062 TFLOPS, while the GTX 1060 3 GB manages 3.935 TFLOPS. The RTX 2070 SUPER also has a significant edge in texture and pixel rates, with 283.2 GTexel/s versus 123.0 GTexel/s, and 113.3 GPixel/s versus 81.98 GPixel/s, respectively.

The RTX 2070 SUPER also wins on raw memory bandwidth, a critical factor for high-resolution textures and compute workloads. Its 448.0 GB/s bandwidth is more than double the GTX 1060 3 GB's 192.2 GB/s, thanks to a 256-bit bus paired with GDDR6 memory, compared to the older card's 192-bit bus and GDDR5. The head-to-head results are unambiguous: the RTX 2070 SUPER wins both tests, with winsA at 2 and winsB at 0. There is no benchmark in this dataset where the GTX 1060 3 GB comes out ahead.

Architecture Differences

The two cards are built on entirely different architectures from different process nodes. The RTX 2070 SUPER uses the TU104 chip, based on Turing architecture, fabricated on a 12 nm process at TSMC. The GTX 1060 3 GB uses the GP106 chip, based on the older Pascal architecture, also from TSMC but on a larger 16 nm node. The transistor counts tell the story of complexity: the RTX 2070 SUPER packs 13,600 million transistors on a 545 mm² die, while the GTX 1060 3 GB has only 4,400 million transistors on a 200 mm² die. This results in a transistor density of 25.0M / mm² for the newer card versus 22.0M / mm² for the older one.

The most significant architectural additions to the RTX 2070 SUPER are the dedicated ray tracing and tensor cores. The RTX 2070 SUPER has 40 RT cores and 320 tensor cores, while the GTX 1060 3 GB has none of either. This is a generational feature gap that cannot be bridged by driver updates or clock speeds. The RTX 2070 SUPER also has a much larger execution engine: 2560 shading units, 160 TMUs, and 64 ROPs, versus 1152 shading units, 72 TMUs, and 48 ROPs on the GTX 1060 3 GB.

Memory technology and capacity differ substantially as well. The RTX 2070 SUPER comes with 8 GB of GDDR6 at 14 Gbps effective, while the GTX 1060 3 GB has 3 GB of GDDR5 at 8 Gbps effective. The memory clock difference is notable: 1750 MHz for the RTX 2070 SUPER versus 2002 MHz for the GTX 1060 3 GB, but the newer card's wider bus and faster memory type deliver far greater effective bandwidth. The RTX 2070 SUPER also supports DirectX 12 Ultimate (12_2), whereas the GTX 1060 3 GB is limited to DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4, but the newer card's feature set is forward-looking.

Where Each One Wins

The RTX 2070 SUPER is the clear winner for any workload that stresses compute, memory bandwidth, or modern API features. Its 208.7% lead in OpenCL and 418.7% lead in Vulkan make it the obvious choice for GPU-accelerated tasks, high-refresh-rate gaming at higher resolutions, and any application that can leverage ray tracing or tensor cores. The data suggests that for users targeting DirectX 12 Ultimate titles or Vulkan-based games, the RTX 2070 SUPER is in a different league. Its 65th percentile ranking among all GPUs, compared to the GTX 1060 3 GB's 64th percentile, understates the gap in these specific tests because the average scores are pulled closer by other factors.

The GTX 1060 3 GB, by contrast, has no benchmark wins in this dataset. Its strengths are relative rather than absolute. It is rated for a 120 W TDP versus 215 W for the RTX 2070 SUPER, and its suggested PSU is 300 W versus 550 W, making it a more power-efficient option for legacy systems. It also uses a single 6-pin power connector, while the RTX 2070 SUPER requires a 6-pin and an 8-pin. For users with older power supplies or smaller cases—the GTX 1060 3 GB is 250 mm long versus 267 mm for the RTX 2070 SUPER—the older card remains a drop-in replacement. However, its 3 GB memory capacity is a hard limit for modern textures, and its lack of RT and tensor cores means it cannot handle ray-traced workloads at all.

In terms of benchmark percentile, the two cards are nearly identical: the RTX 2070 SUPER sits at the 65th percentile, and the GTX 1060 3 GB at the 64th. This suggests that in the broader spectrum of all GPUs, they occupy similar tiers on average, but the head-to-head data shows that the RTX 2070 SUPER's average is buoyed by stronger peak performance in compute-heavy tests. The GTX 1060 3 GB's nearest rivals include the AMD Radeon RX 7900 XTX with a delta of -0.4%, the NVIDIA TITAN Xp at +0.8%, and the NVIDIA GeForce GTX 780 at +0.9%, indicating it performs in line with much older high-end parts.

FAQ

Q: How much faster is the RTX 2070 SUPER in Vulkan compute?

A: The RTX 2070 SUPER scores 90637 in Geekbench Vulkan, which is 418.7% higher than the GTX 1060 3 GB's score of 17475.

Q: What is the memory capacity difference?

A: The RTX 2070 SUPER has 8 GB of GDDR6, while the GTX 1060 3 GB has 3 GB of GDDR5. The newer card also has a 256-bit bus versus a 192-bit bus, resulting in 448.0 GB/s bandwidth versus 192.2 GB/s.

Q: Does the GTX 1060 3 GB support ray tracing?

A: No. The GTX 1060 3 GB has no RT cores, while the RTX 2070 SUPER includes 40 RT cores and 320 tensor cores.

Q: Which card has a higher transistor count?

A: The RTX 2070 SUPER has 13,600 million transistors on a 545 mm² die, compared to 4,400 million on a 200 mm² die for the GTX 1060 3 GB.

Q: What are the power requirements?

A: The RTX 2070 SUPER has a 215 W TDP and requires a 550 W suggested PSU, while the GTX 1060 3 GB has a 120 W TDP and a 300 W suggested PSU.

Q: Are both cards end-of-life?

A: Yes, both are listed as end-of-life production status. The RTX 2070 SUPER was released on 2019-07-08, and the GTX 1060 3 GB on 2016-08-17.

Specification Differences

The two cards differ in nearly every measurable specification. The RTX 2070 SUPER uses the TU104 chip on a 12 nm process, while the GTX 1060 3 GB uses the GP106 chip on a 16 nm process. The transistor count is 13,600 million versus 4,400 million, and the die size is 545 mm² versus 200 mm². The RTX 2070 SUPER has a base clock of 1605 MHz and a boost clock of 1770 MHz, compared to 1506 MHz base and 1708 MHz boost for the GTX 1060 3 GB. Memory clocks differ as well: 1750 MHz (14 Gbps effective) for the newer card versus 2002 MHz (8 Gbps effective) for the older one.

Compute resources are starkly different: 2560 shading units, 160 TMUs, and 64 ROPs for the RTX 2070 SUPER, versus 1152 shading units, 72 TMUs, and 48 ROPs for the GTX 1060 3 GB. The RTX 2070 SUPER has 40 RT cores and 320 tensor cores; the GTX 1060 3 GB has none. Pixel rate is 113.3 GPixel/s versus 81.98 GPixel/s, and texture rate is 283.2 GTexel/s versus 123.0 GTexel/s. FP32 performance is 9.062 TFLOPS versus 3.935 TFLOPS, and FP16 performance is 18.12 TFLOPS (2:1) versus 61.49 GFLOPS (1:64), a massive difference in half-precision compute.

Power and physical specs also diverge. The RTX 2070 SUPER has a 215 W TDP, uses 1x 6-pin + 1x 8-pin power connectors, and requires a 550 W PSU. The GTX 1060 3 GB has a 120 W TDP, uses a single 6-pin connector, and requires a 300 W PSU. The RTX 2070 SUPER is 267 mm long, 116 mm high, and 35 mm wide; the GTX 1060 3 GB is 250 mm long with no listed height or width. Display outputs differ: the RTX 2070 SUPER has 1x HDMI 2.0, 3x DisplayPort 1.4a, and 1x USB Type-C, while the GTX 1060 3 GB has 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a. The DirectX support is 12 Ultimate (12_2) versus 12 (12_1), and the launch MSRP is 499 USD for the RTX 2070 SUPER versus 199 USD for the GTX 1060 3 GB.

DETAILED SPECIFICATIONS

SPECIFICATION
GTX 1060 3 GB
RTX 2070 SUPER
Core Specs
Shading Units
1,152
2,560 +122.2%
Shaders
1,152
2,560 +122.2%
TMUs
72
160 +122.2%
ROPs
48
64 +33.3%
SM Count
9
40 +344.4%
Clocks
Base Clock
1506 MHz
1605 MHz
Boost Clock
1708 MHz
1770 MHz
Memory Clock
2002 MHz 8 Gbps effective
1750 MHz 14 Gbps effective
Memory
Memory Size
3 GB
8 GB
VRAM (MB)
3,072
8,192 +166.7%
Memory Type
GDDR5
GDDR6
Memory Bus
192 bit
256 bit
Bandwidth
192.2 GB/s
448.0 GB/s
Cache
L1 Cache
48 KB (per SM)
64 KB (per SM)
L2 Cache
1536 KB
4 MB
Performance
Pixel Rate
81.98 GPixel/s
113.3 GPixel/s
Texture Rate
123.0 GTexel/s
283.2 GTexel/s
FP32 (TFLOPS)
3.935 TFLOPS
9.062 TFLOPS
FP64 (TFLOPS)
123.0 GFLOPS (1:32)
283.2 GFLOPS (1:32)
FP16 (TFLOPS)
61.49 GFLOPS (1:64)
18.12 TFLOPS (2:1)
AI/RT
RT Cores
—
40
Tensor Cores
—
320
Power
TDP
120 W
215 W
TDP (W)
120
215 +79.2%
Suggested PSU
300 W
550 W
Power Connectors
1x 6-pin
1x 6-pin + 1x 8-pin
Architecture
Architecture
Pascal
Turing
GPU Name
GP106
TU104
Generation
GeForce 10
GeForce 20
Process Size
16 nm
12 nm
Transistors
4,400 million
13,600 million
Die Size
200 mm²
545 mm²
Foundry
TSMC
TSMC
Density
22.0M / mm²
25.0M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
6.1
7.5
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
250 mm 9.8 inches
267 mm 10.5 inches
Height
—
116 mm 4.6 inches
Outputs
1x DVI1x HDMI 2.03x DisplayPort 1.4a
1x HDMI 2.03x DisplayPort 1.4a1x USB Type-C
Bus Interface
PCIe 3.0 x16
PCIe 3.0 x16
Other
Launch Price
199 USD
499 USD
Production
End-of-life
End-of-life
Predecessor
GeForce 900
GeForce 10
Successor
GeForce 20
GeForce 30
View GeForce GTX 1060 3 GB Details View GeForce RTX 2070 SUPER Details