NVIDIA GeForce GTX 1060 6 GB vs NVIDIA GeForce RTX 3070 Mobile Comparison

# NVIDIA GeForce GTX 1060 6 GB vs NVIDIA GeForce RTX 3070 Mobile

The NVIDIA GeForce GTX 1060 6 GB and NVIDIA GeForce RTX 3070 Mobile represent two distinct eras of GPU design, separated by nearly five years of architectural evolution. The GTX 1060, a desktop Pascal part from 2016, faces the RTX 3070 Mobile, an Ampere laptop chip from 2021, and the benchmark data reveals a generational chasm. The RTX 3070 Mobile dominates both shared benchmark tests, delivering roughly 2.9x the OpenCL score and 4.7x the Vulkan score of the GTX 1060, yet both cards sit surprisingly close in overall GPU percentile rankings — 67th for the GTX 1060 versus 65th for the RTX 3070 Mobile. This paradox — massive per-test margins but similar global standing — suggests the GTX 1060's longevity as a desktop staple and the RTX 3070 Mobile's position within a crowded laptop field.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The GTX 1060 6 GB holds an average benchmark score of 21,856, while the RTX 3070 Mobile scores 20,534 — a difference of 1,322 points in favor of the desktop card.

Q: How large is the performance gap in OpenCL compute workloads?

A: The RTX 3070 Mobile scores 92,939 in Geekbench OpenCL versus 32,322 for the GTX 1060, a delta of 65.2% in favor of the laptop GPU.

Q: Do both cards support the same DirectX feature level?

A: No. The GTX 1060 supports DirectX 12 (12_1), while the RTX 3070 Mobile supports DirectX 12 Ultimate (12_2), a newer feature set.

Q: What are the nearest rivals for each card based on average score?

A: The GTX 1060's closest competitor is the AMD Radeon RX 6700S (1.3% faster), while the RTX 3070 Mobile's nearest rival is the Intel Arc B570 (0.1% slower).

Q: Which GPU has more shading units?

A: The RTX 3070 Mobile has 5,120 shading units, exactly four times the 1,280 found on the GTX 1060.

Q: What is the transistor density difference between the two chips?

A: The RTX 3070 Mobile's GA104 chip has a density of 44.4 million transistors per mm², double the 22.0 million per mm² of the GTX 1060's GP106.

Where Each One Wins

The GTX 1060 6 GB wins in overall average benchmark score, posting 21,856 against the RTX 3070 Mobile's 20,534. This aggregate victory, however, is built on a limited benchmark set — the desktop card has three Geekbench entries, while the mobile part carries a broader portfolio including 3DMark and PassMark tests. When examining the two shared workloads, the GTX 1060's advantage evaporates entirely.

The RTX 3070 Mobile claims victory in both head-to-head tests. Its Geekbench OpenCL score of 92,939 crushes the GTX 1060's 32,322, and its Vulkan result of 86,768 more than quadruples the desktop card's 18,659. The mobile GPU also demonstrates strengths in features the GTX 1060 lacks entirely: 40 ray-tracing cores and 160 tensor cores, enabling hardware-accelerated ray tracing and AI workloads. The GTX 1060's wins are confined to its aggregate benchmark average and its higher percentile ranking (67th versus 65th), suggesting that in mixed workloads across its three tested scenarios, it remains competitive in the broader GPU landscape.

Architecture Differences

The GTX 1060 uses the GP106 chip built on TSMC's 16 nm process, packing 4,400 million transistors into a 200 mm² die. The RTX 3070 Mobile employs the GA104 chip fabricated by Samsung on 8 nm, housing 17,400 million transistors across 392 mm². This represents a 3.95x increase in transistor count and a 1.96x increase in die area, with transistor density rising from 22.0 million per mm² to 44.4 million per mm².

Architecturally, the GTX 1060 is a Pascal part with no dedicated ray-tracing or tensor hardware. The RTX 3070 Mobile is Ampere, adding 40 RT cores and 160 tensor cores. The Pascal card's FP16 throughput is severely limited at 68.36 GFLOPS (a 1:64 ratio to FP32), while Ampere delivers full-rate FP16 at 15.97 TFLOPS (1:1 ratio). The mobile GPU also supports DirectX 12 Ultimate (12_2) versus the desktop card's DirectX 12 (12_1), and both cards support OpenGL 4.6 and Vulkan 1.4 equally. The GTX 1060 uses GDDR5 memory on a 192-bit bus, while the RTX 3070 Mobile uses GDDR6 on a 256-bit bus, with memory bandwidth jumping from 192.2 GB/s to 448.0 GB/s.

Specification Differences

The two GPUs diverge on nearly every measurable specification. Memory capacity differs: 6 GB on the GTX 1060 versus 8 GB on the RTX 3070 Mobile. Memory type changes from GDDR5 to GDDR6, and bus width expands from 192-bit to 256-bit. Clock speeds tell an interesting story — the GTX 1060 has a higher base clock (1506 MHz versus 1110 MHz) and boost clock (1709 MHz versus 1560 MHz), yet the RTX 3070 Mobile compensates with vastly more compute units. The mobile card's 5,120 shading units, 160 TMUs, and 80 ROPs dwarf the GTX 1060's 1,280 shading units, 80 TMUs, and 48 ROPs.

Pixel rate nearly doubles from 82.03 GPixel/s to 124.8 GPixel/s, and texture rate jumps from 136.7 GTexel/s to 249.6 GTexel/s. FP32 compute rises from 4.375 TFLOPS to 15.97 TFLOPS, a 3.65x improvement. The GTX 1060 draws 120 W with a 300 W suggested PSU and a 6-pin connector, while the RTX 3070 Mobile is rated at 115 W with no external power connectors, reflecting its portable design. The desktop card uses PCIe 3.0 x16; the mobile part uses PCIe 4.0 x16. Display outputs differ fundamentally: the GTX 1060 offers 1x DVI, 1x HDMI 2.0, and 3x DisplayPort 1.4a, whereas the RTX 3070 Mobile's outputs are "Portable Device Dependent." The GTX 1060 has a launch MSRP of 299 USD; the RTX 3070 Mobile has no listed launch MSRP.

Head-to-Head Benchmarks

The two shared benchmarks reveal a decisive generational gap. In Geekbench OpenCL, the RTX 3070 Mobile scores 92,939 against the GTX 1060's 32,322, a delta of 65.2% favoring the mobile part. This 60,617-point margin aligns with the RTX 3070 Mobile's 3.65x FP32 advantage and its substantially higher texture and pixel rates. The Vulkan test shows an even starker contrast: 86,768 versus 18,659, a 78.5% delta. Here, the RTX 3070 Mobile's score is 4.65x higher, reflecting not just raw compute but also the benefits of newer API optimizations and memory bandwidth.

Contextualizing these results, the RTX 3070 Mobile's nearest rivals include the Intel Arc B570 (0.1% faster) and Intel Arc A750 (0.2% faster), placing it in a competitive mid-range laptop tier. The GTX 1060's nearest rivals — the NVIDIA Quadro RTX 5000 (1% slower), AMD Radeon RX 6700S (1.3% faster), and AMD Radeon RX 5700 (1.4% faster) — show that despite its age, the desktop card still trades blows with much newer hardware in aggregate scoring. The RTX 3070 Mobile's PassMark G3D score of 15,309 and GPU compute score of 6,827 offer additional context, as do its 3DMark Steel Nomad DX12 result of 2,380.

The Verdict

The data paints a clear picture for compute-heavy workloads: the RTX 3070 Mobile is categorically superior in raw performance. Its OpenCL score of 92,939 and Vulkan score of 86,768 leave the GTX 1060's 32,322 and 18,659 far behind. Anyone running GPU-accelerated compute, modern game engines with Vulkan, or ray-traced content should choose the RTX 3070 Mobile without hesitation. The mobile card's 8 GB of GDDR6 memory on a 256-bit bus, yielding 448.0 GB/s bandwidth, further cements its advantage for large datasets.

However, the GTX 1060 6 GB retains a surprising foothold. Its average benchmark score of 21,856 exceeds the RTX 3070 Mobile's 20,534, and its 67th percentile ranking versus 65th suggests that, in the aggregate, it remains relevant. For users on a desktop platform with PCIe 3.0, the GTX 1060's 120 W power draw, 250 mm length, and 6-pin connector make it a straightforward drop-in for legacy systems. It also offers dedicated display outputs including DVI, which the mobile part cannot match. The GTX 1060's higher base and boost clocks (1506/1709 MHz versus 1110/1560 MHz) hint at efficiency in lighter workloads, though its 1:64 FP16 ratio cripples any half-precision compute ambitions.

The verdict hinges on use case. For mobile users needing maximum compute throughput, ray tracing, or modern API support, the RTX 3070 Mobile is the only choice — the 78.5% Vulkan delta alone is decisive. For desktop builders with an older platform, or those prioritizing aggregate benchmark standing and display flexibility, the GTX 1060 remains a functional, if dated, option. The RTX 3070 Mobile's 4x shading units and 3.65x FP32 throughput, however, make it the objectively stronger processor for any future-proofing consideration. The GTX 1060's win in average score is a statistical artifact of limited benchmark overlap, not a genuine performance advantage.