6GB · AI Score 1.3/100 · anchored estimate vs 51 measured cards
1.6 AI Score Includes estimates
We have not run NVIDIA GeForce GTX 1660 Ti on our bench. These figures are anchored estimates, interpolated per workload against the 51 GPUs we did measure (confidence: low). On Qwen3 4B (Q4_K_M) NVIDIA GeForce GTX 1660 Ti should deliver about 82.8 tokens/sec. Llama 3.1 8B does not fit. It needs roughly 8GB and this card has 6GB. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 6GB. 11 of the 12 workloads won't fit on 6GB at the tested precision, Llama 3.1 8B, Qwen2.5-Coder 14B, Qwen3 32B, Llama 3.3 70B and others. We publish those as hard gates rather than quietly dropping to a smaller quant.
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Qwen3-4B | 80.55 tok/s | 73 W44°CQ4_K_M | ✓ Measured |
| Llama-3.1-8B | 49.29 tok/s | 75 W46°CQ4_K_M | ✓ Measured |
| Qwen3 8B | 48.18 tok/s | 75 W48°CQ4_K_M | ✓ Measured |
| Nemotron Nano 9B v2 | ✕ Won't fit needs ~8 GB | VRAM-gated at this precision | Est. |
| Gemma 4 12B | ✕ Won't fit needs ~9 GB | VRAM-gated at this precision | Est. |
| Qwen2.5-Coder 14B | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Qwen3 14B | ✕ Won't fit needs ~11 GB | VRAM-gated at this precision | Est. |
| Gemma 4 26B A4B | ✕ Won't fit needs ~20 GB | VRAM-gated at this precision | Est. |
| Qwen3 30B A3B | ✕ Won't fit needs ~20 GB | VRAM-gated at this precision | Est. |
| Gemma 4 31B | ✕ Won't fit needs ~22 GB | VRAM-gated at this precision | Est. |
| Qwen3 32B | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Llama 3.3 70B | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Sana 1.6B | ✕ Won't fit needs ~11 GB | VRAM-gated at this precision | Est. |
| Stable Diffusion XL | ✕ Won't fit needs ~11 GB | VRAM-gated at this precision | Est. |
| Playground v2.5 | ✕ Won't fit needs ~12 GB | VRAM-gated at this precision | Est. |
| PixArt-Sigma XL | ✕ Won't fit needs ~14 GB | VRAM-gated at this precision | Est. |
| FLUX.1 dev | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Z-Image Turbo | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| FLUX.1 Kontext dev | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Qwen-Image-Edit | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| LTX-Video (distilled) | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Wan 2.2 5B (720p) | ✕ Won't fit | VRAM-gated at this precision | Est. |
| Architecture | Turing (TU116) |
| CUDA cores | 1,536 |
| VRAM | 6GB GDDR6 |
| Memory bus | 192-bit |
| Memory bandwidth | 288 GB/s |
| Boost clock | 1,770 MHz |
| TDP | 120 W |
| Process | 12nm |
| Interface | PCIe 3.0 x16 |
| Release date | 2019-02-22 |
| Launch MSRP | $279 |
NVIDIA GeForce GTX 1660 Ti scores 1.3/100, #98 of 102. It ran 1 of 12; 11 exceeded its 6GB. Figures are anchored estimates, not measurements, we flag that on every row.
100% = this card, AI & Machine Learning headline metric (AI Score). #58 of 61 desktop cards in this vertical.
| GPU | Relative | % | AI Score |
|---|---|---|---|
| NVIDIA GeForce GTX 1080 | 106% | 1.7 | |
| AMD Radeon RX 6700 | 100% | 1.6 | |
| AMD Radeon RX 7600 | 100% | 1.6 | |
| NVIDIA GeForce GTX 1660 Super | 100% | 1.6 | |
| NVIDIA GeForce GTX 1660 Ti | 100% | 1.6 | |
| NVIDIA GeForce GTX 1660 | 94% | 1.5 | |
| Intel Arc A750 | 94% | 1.5 | |
| NVIDIA GeForce RTX 2060 | 81% | 1.3 |
Same card, other workloads: NVIDIA GeForce GTX 1660 Ti Gaming benchmarks
← All AI & Machine Learning GPU rankings
| Transistors | 6,600 million |
| Die size | 284 mm² |
| Process node | 12 nm |
| Fabricated by | TSMC |
| Transistor density | 23.2 million per mm² |
Denser than 64% of the 746 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.
Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.
Whole-job timings, composed from our measured per-model results on this card.
Can't run: 3D game asset kit (needs Stable Diffusion XL), Product shoot, start to finish (needs Stable Diffusion XL), Product photo shoot (needs Stable Diffusion XL), Photo restoration batch (needs FLUX.1 Kontext dev), Restore and enlarge photos (needs FLUX.1 Kontext dev), Character sheet, 12 poses (needs FLUX.1 dev), Short social clips (needs Qwen3 32B), 60-second AI short film (needs Qwen3 32B), 24-frame storyboard (needs Qwen3 32B), 6-panel comic page (needs Qwen3 32B), Long-form article batch (needs Llama 3.3 70B), Full codebase review (needs Qwen2.5-Coder 14B).
This card is $279 to buy. The cheapest listed rate on Vast.ai is $0.082/hour, but that is the floor: we budget $0.098/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 2,835 GPU-hours. Below it you are paying for idle silicon.
| How you would use it | GPU-hours a year | Rental cost a year | Time to break even |
|---|---|---|---|
| 2 hours a day, hobby | 730 | $72 | 3.9 years |
| 8 hours a day, working on it | 2,920 | $287 | 11.7 months |
| 24/7, always-on agent | 8,760 | $862 | 3.9 months |
At steady usage this card pays for itself inside a normal ownership window. Rental figures include a 20% premium over the cheapest listed rate. Ignores electricity, resale and the fact that a rented card can be a newer one tomorrow.
Cheapest of the RunPod and Vast on-demand rates we see, sampled daily. Spot and interruptible pricing runs lower.