NVIDIA GeForce GTX 1060 6 GB vs NVIDIA P106-100 Comparison

NVIDIA
GEFORCE

NVIDIA 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
VS
NVIDIA
GEFORCE

P106-100

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 2017

PERFORMANCE BENCHMARKS

geekbench_metal
14,587
N/A
geekbench_opencl
32,322
35,951
geekbench_vulkan
18,659
32,897
3dmark_3dmark_steel_nomad_dx12
N/A
899

Analysis: NVIDIA GeForce GTX 1060 6 GB vs NVIDIA P106-100

The P106-100 and the GTX 1060 6 GB share the same GP106 silicon, the same 16 nm TSMC process, and identical core counts, yet their benchmark results diverge sharply in specific workloads. The P106-100 is a mining-focused card with no display outputs, while the GTX 1060 6 GB is a full retail graphics card. In the two shared benchmark tests, the P106-100 wins both, with a commanding 76.3% lead in Vulkan and a solid 11.2% advantage in OpenCL. However, the GTX 1060 6 GB carries a launch MSRP of 299 USD and includes standard display connectivity, making it the more versatile product despite lower raw scores in these particular tests.

Where Each One Wins

The data splits these two cards along a clear functional line. The P106-100 is optimized for compute-heavy tasks, particularly those that leverage asynchronous compute or low-level API access. Its Geekbench Vulkan score of 32897 crushes the GTX 1060 6 GB’s 18659, a delta of 76.3%. This is not a marginal advantage; it indicates that the P106-100’s architecture is tuned for the kind of parallel workload execution that Vulkan exposes. For any application that uses Vulkan for rendering or compute, the P106-100 is decisively faster.

The OpenCL results tell a similar but less extreme story. The P106-100 scores 35951 against the GTX 1060 6 GB’s 32322, an 11.2% lead. OpenCL is more general-purpose, and while the P106-100 still wins, the gap is narrower. This suggests that the P106-100’s advantage grows when the workload moves to a lower-level, more direct hardware interface like Vulkan, whereas in OpenCL the two cards are closer in raw throughput.

The GTX 1060 6 GB has no benchmark wins in the head-to-head data. That does not mean it is without merit — it has a higher percentile rank among all GPUs (67th vs 68th for the P106-100, a negligible difference) and a richer feature set for actual use. But in pure computational benchmarks, the P106-100 takes both tests. The GTX 1060 6 GB’s strength lies not in raw compute scores but in its role as a complete graphics card: it has display outputs (1x DVI, 1x HDMI 2.0, 3x DisplayPort 1.4a) and a standard PCIe 3.0 x16 interface, whereas the P106-100 has no display outputs and only a PCIe 1.0 x16 interface. For gaming or any visual output, the GTX 1060 6 GB is the only option of the two, even if its compute scores trail.

Architecture Differences

Both cards are built on the same GP106 chip, fabricated by TSMC on a 16 nm process, with 4,400 million transistors on a 200 mm² die. The transistor density is identical at 22.0M / mm². The core configuration is also the same: 1280 shading units, 80 texture mapping units, and 48 ROPs. Clock speeds match exactly — 1506 MHz base and 1709 MHz boost — and memory is identical: 6 GB of GDDR5 on a 192-bit bus, delivering 192.2 GB/s of bandwidth. Pixel rate (82.03 GPixel/s), texture rate (136.7 GTexel/s), and FP32 throughput (4.375 TFLOPS) are all equal. Even the FP16 rate is the same at 68.36 GFLOPS (1:64), indicating that neither card has meaningful half-precision acceleration.

The architectural divergence is in the surrounding platform, not the silicon itself. The P106-100 uses a PCIe 1.0 x16 bus interface, while the GTX 1060 6 GB uses PCIe 3.0 x16. This is a significant difference for data transfer between the CPU and GPU, though it does not affect on-chip compute performance. The P106-100 has no display outputs, meaning it cannot drive a monitor; the GTX 1060 6 GB offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a. The P106-100 is listed under the "Mining GPUs" generation, while the GTX 1060 6 GB belongs to the "GeForce 10" series. The GTX 1060 6 GB has a predecessor (GeForce 900) and a successor (GeForce 20), whereas the P106-100 has neither. Both are end-of-life products, and both consume 120 W with a dual-slot cooler and a single 6-pin power connector, requiring a 300 W power supply.

The API support is identical: DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. Neither card has ray tracing cores or tensor cores. The physical dimensions are the same length (250 mm / 9.8 inches), and the GTX 1060 6 GB also lists a height of 111 mm / 4.4 inches, which the P106-100 does not specify. The core architectural story is that these are the same GPU, but the P106-100 is stripped of display functionality and hobbled by an older PCIe interface, while the GTX 1060 6 GB is a full retail package.

Head-to-Head Benchmarks

The two shared benchmarks reveal a stark performance split. In Geekbench OpenCL, the P106-100 scores 35951 against the GTX 1060 6 GB’s 32322, a delta of 11.2%. The P106-100 wins this test. This is a moderate but clear advantage, suggesting that the P106-100 handles OpenCL compute workloads with greater efficiency, possibly due to its mining-oriented firmware or driver optimizations that favor raw compute over graphics pipeline overhead.

The Geekbench Vulkan test is where the P106-100 truly separates itself. It scores 32897, while the GTX 1060 6 GB manages only 18659. The delta is 76.3%, a massive gap that dwarfs the OpenCL difference. Vulkan is a low-overhead API that gives the GPU more direct control over its hardware. The P106-100’s 76.3% lead indicates that it is substantially better at executing the kind of command buffer submission and draw call handling that Vulkan emphasizes. For developers targeting Vulkan, the P106-100 is more than three-quarters faster, which is a decisive margin in any benchmark comparison.

In the overall average benchmark score, the P106-100 sits at 23249 against the GTX 1060 6 GB’s 21856. That is a difference of roughly 1393 points, or about 6.4% in favor of the P106-100. The P106-100’s percentile rank among all GPUs is 68, versus 67 for the GTX 1060 6 GB — a difference of one percentile point, effectively a tie in the broader GPU landscape. The nearest rivals for the P106-100 include the AMD Radeon Pro Vega 16 (avg score 23250, 0% delta) and the AMD Radeon RX 6600M (avg score 23273, -0.1% delta), showing that the P106-100 sits in a tight cluster of mid-range performers. The GTX 1060 6 GB’s nearest rivals include the NVIDIA Quadro RTX 5000 (avg score 21629, 1% delta) and the AMD Radeon RX 6700S (avg score 22154, -1.3% delta), indicating it is slightly lower in the performance hierarchy but still within a few percent of similar cards.

Specification Differences

The two cards differ in a handful of fields, while sharing most core specifications. The bus interface is a key difference: the P106-100 uses PCIe 1.0 x16, while the GTX 1060 6 GB uses PCIe 3.0 x16. This affects host-to-device transfer speeds but not on-chip compute. Display outputs are another major difference: the P106-100 has no outputs, whereas the GTX 1060 6 GB provides 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a. The generation field differs: the P106-100 is listed under "Mining GPUs," while the GTX 1060 6 GB is in the "GeForce 10" series. The GTX 1060 6 GB also has a predecessor (GeForce 900) and successor (GeForce 20), while the P106-100 has neither. The GTX 1060 6 GB lists a height of 111 mm / 4.4 inches; the P106-100 does not. The launch MSRP exists only for the GTX 1060 6 GB at 299 USD; the P106-100 has no listed launch MSRP. Release dates differ: the P106-100 launched on 2017-06-18, and the GTX 1060 6 GB on 2016-07-18. All other specification fields — process node, transistor count, die size, clock speeds, memory, shading units, TMUs, ROPs, pixel rate, texture rate, FP32, FP16, TDP, slot width, power connectors, suggested PSU, and API support — are identical.

FAQ

Q: Which card has a higher average benchmark score?

A: The NVIDIA P106-100 has an average benchmark score of 23249, while the NVIDIA GeForce GTX 1060 6 GB scores 21856. The P106-100 is ahead by roughly 1393 points.

Q: How much faster is the P106-100 in Vulkan?

A: In the Geekbench Vulkan test, the P106-100 scores 32897 compared to the GTX 1060 6 GB’s 18659, a delta of 76.3% in favor of the P106-100.

Q: Do both cards have the same memory configuration?

A: Yes, both use 6 GB of GDDR5 memory on a 192-bit bus with 192.2 GB/s bandwidth. The memory clock is 2002 MHz (8 Gbps effective) for both.

Q: Can the P106-100 output video to a display?

A: No, the P106-100 has no display outputs. The GTX 1060 6 GB has 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a.

Q: What is the percentile rank difference between the two cards?

A: The P106-100 is in the 68th percentile among all GPUs, and the GTX 1060 6 GB is in the 67th percentile. The difference is one percentile point.

Q: Is the GTX 1060 6 GB’s predecessor and successor listed?

A: Yes, the GTX 1060 6 GB has a predecessor of GeForce 900 and a successor of GeForce 20. The P106-100 has neither listed.

DETAILED SPECIFICATIONS

SPECIFICATION
GTX 1060 6 GB
P106-100
Core Specs
Shading Units
1,280
1,280 0.0%
Shaders
1,280
1,280 0.0%
TMUs
80
80 0.0%
ROPs
48
48 0.0%
SM Count
10
10 0.0%
Clocks
Base Clock
1506 MHz
1506 MHz
Boost Clock
1709 MHz
1709 MHz
Memory Clock
2002 MHz 8 Gbps effective
2002 MHz 8 Gbps effective
Memory
Memory Size
6 GB
6 GB
VRAM (MB)
6,144
6,144 0.0%
Memory Type
GDDR5
GDDR5
Memory Bus
192 bit
192 bit
Bandwidth
192.2 GB/s
192.2 GB/s
Cache
L1 Cache
48 KB (per SM)
48 KB (per SM)
L2 Cache
1536 KB
1536 KB
Performance
Pixel Rate
82.03 GPixel/s
82.03 GPixel/s
Texture Rate
136.7 GTexel/s
136.7 GTexel/s
FP32 (TFLOPS)
4.375 TFLOPS
4.375 TFLOPS
FP64 (TFLOPS)
136.7 GFLOPS (1:32)
136.7 GFLOPS (1:32)
FP16 (TFLOPS)
68.36 GFLOPS (1:64)
68.36 GFLOPS (1:64)
Power
TDP
120 W
120 W
TDP (W)
120
120 0.0%
Suggested PSU
300 W
300 W
Power Connectors
1x 6-pin
1x 6-pin
Architecture
Architecture
Pascal
Pascal
GPU Name
GP106
GP106
Generation
GeForce 10
Mining GPUs
Process Size
16 nm
16 nm
Transistors
4,400 million
4,400 million
Die Size
200 mm²
200 mm²
Foundry
TSMC
TSMC
Density
22.0M / mm²
22.0M / mm²
API Support
DirectX
12 (12_1)
12 (12_1)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
6.1
6.1
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
250 mm 9.8 inches
250 mm 9.8 inches
Height
111 mm 4.4 inches
—
Outputs
1x DVI1x HDMI 2.03x DisplayPort 1.4a
No outputs
Bus Interface
PCIe 3.0 x16
PCIe 1.0 x16
Other
Launch Price
299 USD
—
Production
End-of-life
End-of-life
Predecessor
GeForce 900
—
Successor
GeForce 20
—
View GeForce GTX 1060 6 GB Details View P106-100 Details