NVIDIA GeForce GTX 1660 Ti vs NVIDIA T600 Comparison

The NVIDIA GeForce GTX 1660 Ti is the decisive performance winner, taking 8 of 9 head-to-head benchmarks and posting massive leads in raw compute and DirectX workloads. The NVIDIA T600, however, claims a single, enormous victory in Vulkan, which highlights a starkly different performance profile that makes it relevant for specific software stacks.

Architecture Differences

Both GPUs are built on NVIDIA’s Turing architecture, but they are implemented with different chips and target very different segments. The GTX 1660 Ti uses the TU116 chip, fabricated on a 12 nm process at TSMC, containing 6,600 million transistors on a 284 mm² die. The T600 uses the smaller TU117 chip, also on TSMC’s 12 nm process, with 4,700 million transistors on a 200 mm² die. Despite the smaller absolute transistor count, the T600’s transistor density is marginally higher at 23.5M / mm² versus 23.2M / mm² for the GTX 1660 Ti.

The compute configuration diverges sharply. The GTX 1660 Ti packs 1,536 shading units, 96 texture mapping units, and 48 render output units. The T600 is cut down to 640 shading units, 40 TMUs, and 32 ROPs. This nearly 2.4x advantage in shader count for the GTX 1660 Ti directly explains its dominance in most tests. Neither card includes dedicated ray tracing or tensor cores, keeping both firmly in the rasterization-focused tier of Turing.

Memory subsystems also differ. The GTX 1660 Ti features 6 GB of GDDR6 on a 192-bit bus, delivering 288.0 GB/s of bandwidth with memory clocked at 12 Gbps effective. The T600 has 4 GB of GDDR6 on a narrower 128-bit bus, yielding 160.0 GB/s at 10 Gbps effective. The GTX 1660 Ti’s 80% bandwidth advantage is critical for texture-heavy and high-resolution workloads.

Clock speeds tell a similar story. The GTX 1660 Ti runs at a 1500 MHz base and 1770 MHz boost, while the T600 operates at a much lower 735 MHz base and 1335 MHz boost. The combination of more cores and higher clocks gives the GTX 1660 Ti a theoretical FP32 throughput of 5.437 TFLOPS, over three times the T600’s 1.709 TFLOPS. Pixel rate and texture rate follow suit: 84.96 GPixel/s and 169.9 GTexel/s for the GTX 1660 Ti versus 42.72 GPixel/s and 53.40 GTexel/s for the T600.

Thermal and physical design highlights the intended use cases. The GTX 1660 Ti is a dual-slot card with a 120 W TDP, requiring a 1x 8-pin power connector and a 300 W suggested PSU. The T600 is a single-slot, 40 W card with no power connectors and a 200 W suggested PSU. The GTX 1660 Ti is also physically larger at 229 mm long and 111 mm tall, while the T600’s dimensions are not listed, though its single-slot profile implies a compact footprint. Display outputs differ as well: the GTX 1660 Ti offers 1x DVI, 1x HDMI 2.0, and 1x DisplayPort 1.4a, while the T600 provides 4x mini-DisplayPort 1.4a.

Head-to-Head Benchmarks

The GTX 1660 Ti wins every benchmark except one, and the margins are often enormous. In 3DMark Steel Nomad DX12, the GTX 1660 Ti scores 1061 against the T600’s absence from that test, though the T600 is not listed in that specific benchmark. In the nine shared tests, the GTX 1660 Ti’s smallest victory is in Passmark G2D, where it scores 804 versus 756, a modest 6.3% lead. Every other win is substantial.

The biggest deltas come in compute and DirectX. In Passmark GPU Compute, the GTX 1660 Ti scores 5226 against 2402, a 117.6% advantage. Passmark DirectX 11 shows a 110.2% lead (103 vs 49), and Passmark DirectX 10 shows 106.3% (66 vs 32). Passmark DirectX 12 follows closely at 104% (51 vs 25). The GTX 1660 Ti also dominates in Passmark G3D, scoring 12871 versus 6479, a 98.7% lead. Even in DirectX 9, a legacy API, the GTX 1660 Ti leads by 66.7% (190 vs 114). In Geekbench OpenCL, the GTX 1660 Ti scores 51029 versus 27875, an 83.1% advantage.

The single exception is Geekbench Vulkan, where the T600 scores 25580 against the GTX 1660 Ti’s 5827. That is a 77.2% lead for the T600 in the GTX 1660 Ti’s direction, meaning the T600 is 77.2% ahead. This is a remarkable reversal given the T600’s far lower raw specs. The T600’s average benchmark score is 7035, and its nearest rival is the NVIDIA GeForce GTX 970 with a delta of -1.7%, indicating it slightly underperforms that older card in aggregate. The GTX 1660 Ti’s average is 7723, putting it 0.7% ahead of the AMD Radeon 540.

Where Each One Wins

The GTX 1660 Ti is the clear choice for any workload that relies on raw rasterization throughput, DirectX API performance, or general compute. Its Passmark G3D score of 12871 is nearly double the T600’s 6479, making it overwhelmingly faster for gaming and 3D rendering tasks that use DirectX 9 through 12. The 117.6% lead in GPU compute suggests strong performance in OpenCL-based applications, though the Geekbench OpenCL result (83.1% ahead) corroborates this. The GTX 1660 Ti also holds a slim but real advantage in 2D performance, winning Passmark G2D by 6.3%.

The T600’s only win is in Geekbench Vulkan, where its 25580 score crushes the GTX 1660 Ti’s 5827. This is not a small margin; it is a 77.2% lead. This suggests that for software specifically optimized for the Vulkan API, the T600’s architecture or driver stack delivers outsized results that its modest specs do not predict. The T600’s 4x mini-DisplayPort outputs also make it a natural fit for multi-monitor setups in enterprise environments, though this is a feature difference rather than a benchmark win. Its 40 W TDP and single-slot design allow for deployment in low-power or space-constrained systems where the GTX 1660 Ti’s 120 W dual-slot footprint would be impractical.

The Verdict

From the data, the NVIDIA GeForce GTX 1660 Ti is the superior performer for the vast majority of use cases. Its 8-1 benchmark win count, including leads of over 100% in three DirectX tests and nearly 100% in G3D, makes it the definitive choice for gaming, DirectX-based rendering, and general compute. The GTX 1660 Ti’s 6 GB of VRAM and 288.0 GB/s bandwidth further reinforce its suitability for modern workloads that demand large memory pools and high throughput. Its 41st percentile ranking among all GPUs is modest, but it is ahead of the T600’s 39th percentile.

The T600 is not without merit, but its appeal is narrow. The Vulkan result is the single most compelling reason to consider it; a 77.2% lead in that API is undeniable. For developers or users locked into Vulkan-centric applications, the T600 could be the faster card despite its lower specs. Its 4 GB memory and 160.0 GB/s bandwidth are sufficient for many professional tasks, and its single-slot, 40 W design with no power connector is ideal for compact workstations. The T600’s average score of 7035 is close to that of the GTX 1660 Ti’s 7723, but the distribution of wins is lopsided.

Choose the GTX 1660 Ti if you need broad, high-performance acceleration across DirectX and compute workloads. Choose the T600 only if your primary software is Vulkan-based and you prioritize that specific benchmark, or if your system constraints demand a single-slot, low-power card. The data does not support the T600 as a general-purpose alternative; it wins one test, and the GTX 1660 Ti wins the rest by margins ranging from 6.3% to 117.6%. The GTX 1660 Ti is the verdict for almost everyone.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA GeForce GTX 1660 Ti has an average benchmark score of 7723, while the NVIDIA T600 averages 7035.

Q: How large is the performance gap in Passmark G3D?

A: The GTX 1660 Ti scores 12871 in Passmark G3D versus 6479 for the T600, a 98.7% lead.

Q: Is there any benchmark where the T600 wins?

A: Yes, the T600 wins Geekbench Vulkan with a score of 25580 against the GTX 1660 Ti’s 5827, a 77.2% lead.

Q: What are the memory capacities and bandwidths?

A: The GTX 1660 Ti has 6 GB of GDDR6 on a 192-bit bus with 288.0 GB/s bandwidth. The T600 has 4 GB of GDDR6 on a 128-bit bus with 160.0 GB/s bandwidth.

Q: How do their power requirements compare?

A: The GTX 1660 Ti has a 120 W TDP, requires a 1x 8-pin power connector, and suggests a 300 W PSU. The T600 has a 40 W TDP, needs no power connector, and suggests a 200 W PSU.

Q: What is the transistor density difference?

A: The T600 has a slightly higher transistor density at 23.5M / mm², compared to 23.2M / mm² for the GTX 1660 Ti.

Specification Differences

| Specification | NVIDIA GeForce GTX 1660 Ti | NVIDIA T600 |

| --- | --- | --- |

| Chip | TU116 | TU117 |

| Generation | GeForce 16 | Quadro Turing (Tx000) |

| Transistors | 6,600 million | 4,700 million |

| Die Size | 284 mm² | 200 mm² |

| Transistor Density | 23.2M / mm² | 23.5M / mm² |

| Base Clock | 1500 MHz | 735 MHz |

| Boost Clock | 1770 MHz | 1335 MHz |

| Memory Clock | 12 Gbps effective | 10 Gbps effective |

| Memory Size | 6 GB | 4 GB |

| Memory Bus Width | 192 bit | 128 bit |

| Memory Bandwidth | 288.0 GB/s | 160.0 GB/s |

| Shading Units | 1536 | 640 |

| TMUs | 96 | 40 |

| ROPs | 48 | 32 |

| Pixel Rate | 84.96 GPixel/s | 42.72 GPixel/s |

| Texture Rate | 169.9 GTexel/s | 53.40 GTexel/s |

| FP32 | 5.437 TFLOPS | 1.709 TFLOPS |

| FP16 | 10.87 TFLOPS (2:1) | 3.418 TFLOPS (2:1) |

| TDP | 120 W | 40 W |

| Slot Width | Dual-slot | Single-slot |

| Power Connectors | 1x 8-pin | None |

| Suggested PSU | 300 W | 200 W |

| Display Outputs | 1x DVI, 1x HDMI 2.0, 1x DisplayPort 1.4a | 4x mini-DisplayPort 1.4a |

| Length | 229 mm | Not listed |

| Height | 111 mm | Not listed |

| Width | 35 mm | Not listed |

| Release Date | 2019-02-21 | 2021-04-11 |

| Predecessor | GeForce 10 | Quadro Volta |

| Successor | GeForce 20 | Workstation Ampere |

| Launch MSRP | 279 USD | Not listed |

| Avg Benchmark Score | 7723 | 7035 |

| Percentile vs All GPUs | 41 | 39 |