AMD Radeon RX 6700S vs NVIDIA GeForce GTX 1060 3 GB Comparison

AMD
RADEON

AMD Radeon RX 6700S

CORE STATE Navi 23
VRAM 8 GB
CLOCK SPEED 2000 MHz
TDP 80 W
BUS WIDTH 128 bit
ARCHITECTURE RDNA 2.0
nm
PROCESS 7 nm
LAUNCH DATE 2022
VS
NVIDIA
GEFORCE

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

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
1,451
N/A
geekbench_metal
72,864
13,527
geekbench_opencl
70,965
27,001
geekbench_vulkan
76,150
17,475
passmark_directx_10
87
N/A
passmark_directx_11
134
N/A
passmark_directx_12
58
N/A
passmark_directx_9
195
N/A
passmark_g2d
739
N/A
passmark_g3d
15,066
N/A
passmark_gpu_compute
5,990
N/A

Analysis: AMD Radeon RX 6700S vs NVIDIA GeForce GTX 1060 3 GB

# AMD Radeon RX 6700S vs NVIDIA GeForce GTX 1060 3 GB

The AMD Radeon RX 6700S is a mobile-focused GPU built on TSMC's 7 nm process with RDNA 2.0 architecture, while the NVIDIA GeForce GTX 1060 3 GB is a desktop Pascal card from 2016. The database shows a clear generational gap: the RX 6700S holds an average benchmark score of 22,154 versus 19,334 for the GTX 1060 3 GB, placing the AMD part at the 67th percentile of all GPUs compared to the NVIDIA card's 64th percentile. In the three head-to-head compute tests recorded, the RX 6700S wins every round, with deltas ranging from 162.8% to 438.7%.

Where Each One Wins

The RX 6700S dominates every recorded benchmark category, but the nature of its wins differs by workload. In Geekbench Metal, the AMD card scores 72,864 against 13,527 for the GTX 1060 3 GB, a staggering 438.7% advantage. This is the largest gap in the dataset and reflects the AMD card's modern architecture and much higher raw throughput. Metal is a low-level API favored by Apple platforms, and the RX 6700S's RDNA 2.0 design with 1792 shading units simply overwhelms the older Pascal chip's 1152 units.

For OpenCL, the RX 6700S posts 70,965 versus 27,001, a 162.8% lead. OpenCL is a cross-platform compute standard, and this result shows the AMD card's advantage in general-purpose GPU compute. The GTX 1060 3 GB's 3.935 TFLOPS of FP32 throughput is less than half of the RX 6700S's 7.168 TFLOPS, explaining the gap.

In Vulkan, the RX 6700S scores 76,150 against 17,475, a 335.8% margin. Vulkan is the modern gaming and compute API, and here the AMD card's support for DirectX 12 Ultimate (12_2) and Vulkan 1.4 gives it both architectural and software-level advantages. The GTX 1060 3 GB only supports DirectX 12 (12_1) and Vulkan 1.4, but its older Pascal design lacks the dedicated ray tracing cores and other RDNA 2.0 features.

The GTX 1060 3 GB does not win any of the three head-to-head tests. Its only notable advantage in the database is its form factor: it is a dual-slot desktop card with a 250 mm length and a 6-pin power connector, whereas the RX 6700S is an IGP (integrated graphics package) for portable devices with no power connector. For users building a desktop with legacy PCIe 3.0, the GTX 1060 3 GB remains functional, but in pure benchmark terms, the RX 6700S is ahead everywhere.

Architecture Differences

The two GPUs come from different eras and design philosophies. The RX 6700S uses the Navi 23 chip on TSMC's 7 nm process, packing 11,060 million transistors into a 237 mm² die. This yields a transistor density of 46.7M per mm², a figure that reflects the modern manufacturing node. The GTX 1060 3 GB uses the GP106 chip on TSMC's 16 nm process, with 4,400 million transistors on a 200 mm² die, giving a density of 22.0M per mm². The RX 6700S has 2.5 times the transistor count and more than double the density.

Clock speeds also differ significantly. The RX 6700S runs at a base of 1700 MHz, a boost of 2000 MHz, and a game clock of 1890 MHz. The GTX 1060 3 GB has a base of 1506 MHz and a boost of 1708 MHz. The AMD card's higher clocks, combined with its larger shader count, produce a substantial compute advantage: 7.168 TFLOPS FP32 versus 3.935 TFLOPS. The FP16 comparison is even more lopsided: the RX 6700S delivers 14.34 TFLOPS at a 2:1 ratio, while the GTX 1060 3 GB manages only 61.49 GFLOPS at a 1:64 ratio, meaning it essentially lacks practical FP16 throughput.

Memory is another major divider. The RX 6700S uses 8 GB of GDDR6 on a 128-bit bus, delivering 224.0 GB/s of bandwidth. The GTX 1060 3 GB uses 3 GB of GDDR5 on a 192-bit bus, with 192.2 GB/s. Although the NVIDIA card has a wider bus, the AMD card's faster GDDR6 memory (14 Gbps effective versus 8 Gbps effective) gives it higher total bandwidth. The 3 GB capacity on the GTX 1060 is a clear limitation for modern workloads, while 8 GB on the RX 6700S is far more practical.

Feature support also diverges. The RX 6700S includes 28 ray tracing cores and supports DirectX 12 Ultimate (12_2), while the GTX 1060 3 GB has no ray tracing cores and only DirectX 12 (12_1). The AMD card also supports PCIe 4.0 x8, whereas the GTX 1060 3 GB uses PCIe 3.0 x16. Both support OpenGL 4.6 and Vulkan 1.4. Power consumption tells the story of efficiency: the RX 6700S is rated at 80 W TDP despite its higher performance, while the GTX 1060 3 GB draws 120 W and requires a 300 W suggested PSU. This efficiency gap is a direct result of the 7 nm versus 16 nm process difference.

Head-to-Head Benchmarks

The database records three direct comparisons between these two GPUs, and the RX 6700S wins all three with margins that range from substantial to extreme.

In Geekbench Metal, the RX 6700S scores 72,864 versus 13,527 for the GTX 1060 3 GB. This is a 438.7% delta, meaning the AMD card delivers more than five times the Metal performance. Metal is optimized for Apple's ecosystem, and the RX 6700S's RDNA 2.0 architecture with its high FP32 and FP16 throughput is clearly better suited to this API. The GTX 1060 3 GB's Pascal architecture, which lacks dedicated compute features and has a 1:64 FP16 ratio, struggles mightily here.

In Geekbench OpenCL, the RX 6700S posts 70,965 while the GTX 1060 3 GB manages 27,001. The 162.8% delta is the smallest of the three tests, but still a decisive victory. OpenCL is a general-purpose compute workload, and the RX 6700S's 1792 shading units at 2000 MHz boost clock provide roughly double the raw throughput of the GTX 1060 3 GB's 1152 units at 1708 MHz. The memory bandwidth advantage (224.0 GB/s versus 192.2 GB/s) also helps in memory-bound compute tasks.

In Geekbench Vulkan, the RX 6700S scores 76,150 against 17,475, a 335.8% margin. Vulkan is the modern cross-platform gaming API, and here the RX 6700S's DirectX 12 Ultimate support and Vulkan 1.4 compatibility give it a strong edge. The GTX 1060 3 GB also supports Vulkan 1.4, but its older architecture lacks the asynchronous compute and other modern features that RDNA 2.0 brings. The 3 GB VRAM limit may also constrain Vulkan workloads that need more memory.

The average benchmark score reinforces this trend: the RX 6700S averages 22,154, while the GTX 1060 3 GB averages 19,334. The RX 6700S sits close to the AMD Radeon RX 5700 (22,170, a -0.1% delta) and the NVIDIA GeForce RTX 5060 Mobile (22,435, a -1.3% delta). The GTX 1060 3 GB, meanwhile, is near the AMD Radeon RX 7900 XTX (19,410, a -0.4% delta) and the NVIDIA TITAN Xp (19,177, a 0.8% delta), which places it in a much older performance tier.

The Verdict

The data is unambiguous: the AMD Radeon RX 6700S outperforms the NVIDIA GeForce GTX 1060 3 GB in every recorded benchmark, with deltas that range from 162.8% to 438.7%. The RX 6700S is the pick for anyone who needs modern compute performance, ray tracing support, more VRAM, and far better efficiency. Its 80 W TDP versus 120 W, its 8 GB GDDR6 versus 3 GB GDDR5, and its 7 nm node versus 16 nm all point to a GPU that is simply in a different class.

The GTX 1060 3 GB, however, still has a niche. It is a dual-slot desktop card with a 6-pin power connector, making it easy to install in legacy systems. It supports PCIe 3.0 x16, which is fine for older motherboards. Its 250 mm length fits most cases. For users who need a basic GPU for light gaming or desktop tasks on an older platform, it remains a functional option. But its 3 GB VRAM is a hard limit for modern titles, and its lack of ray tracing cores and low FP16 throughput make it unsuitable for current-generation workloads.

From the database's perspective, the RX 6700S is the clear winner for compute, gaming, and efficiency. The GTX 1060 3 GB wins only on legacy compatibility and physical form factor. Choose the RX 6700S for performance and future-proofing; choose the GTX 1060 3 GB only if you need a drop-in desktop card with minimal power requirements and do not need modern features.

FAQ

Q: Which GPU has higher raw compute performance?

A: The AMD Radeon RX 6700S delivers 7.168 TFLOPS FP32 and 14.34 TFLOPS FP16 (2:1), while the NVIDIA GeForce GTX 1060 3 GB offers 3.935 TFLOPS FP32 and 61.49 GFLOPS FP16 (1:64).

Q: How much VRAM does each card have, and what type?

A: The RX 6700S has 8 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth. The GTX 1060 3 GB has 3 GB of GDDR5 on a 192-bit bus with 192.2 GB/s bandwidth.

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

A: No. The GTX 1060 3 GB has no ray tracing cores, while the RX 6700S includes 28 ray tracing cores and supports DirectX 12 Ultimate (12_2).

Q: What is the power consumption difference?

A: The RX 6700S is rated at 80 W TDP with no power connector, while the GTX 1060 3 GB is rated at 120 W TDP with a 6-pin power connector and a suggested 300 W PSU.

Q: Which card wins in Geekbench Vulkan?

A: The RX 6700S scores 76,150 versus 17,475 for the GTX 1060 3 GB, a 335.8% advantage.

Q: How do these cards compare to their nearest rivals?

A: The RX 6700S (average 22,154) is nearly identical to the RX 5700 (22,170, -0.1%) and slightly behind the RTX 5060 Mobile (22,435, -1.3%). The GTX 1060 3 GB (average 19,334) is comparable to the RX 7900 XTX (19,410, -0.4%) and the TITAN Xp (19,177, 0.8%).

DETAILED SPECIFICATIONS

SPECIFICATION
RX 6700S
GTX 1060 3 GB
Core Specs
Shading Units
1,792
1,152 -35.7%
Shaders
1,792
1,152 -35.7%
TMUs
112
72 -35.7%
ROPs
64
48 -25.0%
Compute Units
28
—
SM Count
—
9
Clocks
Base Clock
1700 MHz
1506 MHz
Boost Clock
2000 MHz
1708 MHz
Game Clock
1890 MHz
—
Memory Clock
1750 MHz 14 Gbps effective
2002 MHz 8 Gbps effective
Memory
Memory Size
8 GB
3 GB
VRAM (MB)
8,192
3,072 -62.5%
Memory Type
GDDR6
GDDR5
Memory Bus
128 bit
192 bit
Bandwidth
224.0 GB/s
192.2 GB/s
Cache
L1 Cache
128 KB per Array
48 KB (per SM)
L2 Cache
2 MB
1536 KB
L3 Cache
32 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
128.0 GPixel/s
81.98 GPixel/s
Texture Rate
224.0 GTexel/s
123.0 GTexel/s
FP32 (TFLOPS)
7.168 TFLOPS
3.935 TFLOPS
FP64 (TFLOPS)
448.0 GFLOPS (1:16)
123.0 GFLOPS (1:32)
FP16 (TFLOPS)
14.34 TFLOPS (2:1)
61.49 GFLOPS (1:64)
AI/RT
RT Cores
28
—
Power
TDP
80 W
120 W
TDP (W)
80
120 +50.0%
Suggested PSU
—
300 W
Power Connectors
None
1x 6-pin
Architecture
Architecture
RDNA 2.0
Pascal
GPU Name
Navi 23
GP106
Generation
Navi Mobile (RX 6000M)
GeForce 10
Process Size
7 nm
16 nm
Transistors
11,060 million
4,400 million
Die Size
237 mm²
200 mm²
Foundry
TSMC
TSMC
Density
46.7M / mm²
22.0M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
3.0
CUDA
—
6.1
Shader Model
6.8
6.8
Physical
Slot Width
IGP
Dual-slot
Length
—
250 mm 9.8 inches
Outputs
Portable Device Dependent
1x DVI1x HDMI 2.03x DisplayPort 1.4a
Bus Interface
PCIe 4.0 x8
PCIe 3.0 x16
Other
Launch Price
—
199 USD
Production
End-of-life
End-of-life
Predecessor
Polaris Mobile
GeForce 900
Successor
—
GeForce 20
View Radeon RX 6700S Details View GeForce GTX 1060 3 GB Details