GTX 1660 Super
44 AI models fit in 6 GB VRAM at Q4 native. 13 more run with CPU offloading. Real benchmarks below.
llama.cpp 0.2.x · CUDA 12 · Ubuntu 22.04 · Prices verified on Amazon · methodology →
Execution Context
Ver oferta atual
Amazon affiliate link for GTX 1660 Super
Alguns links são links de afiliado da Amazon. Podemos receber uma comissão sem custo adicional para si. O cookie da Amazon pode durar até 24 horas após o clique.
Full Specifications
NVIDIA · 2019-10
| VRAM | 6 GB GDDR6 |
| Bandwidth | 336 GB/s |
| FP16 TFLOPS | 5.03 |
| AI Score | 18 / 140 |
| CUDA Cores | 1,408 |
| TDP | 125 W |
| PCIe | Gen 3 |
| Slots | 2 |
| Power Connector | 8-pin |
| Price Band | Entrada |
| Released | 2019-10 |
AI Benchmarks
Real inference measurements — llama.cpp Q4_K_M
| Task | Result |
|---|---|
| Llama 1B Q4 | 176 tok/s |
| Llama 3B Q4 | 70 tok/s |
| Llama 7B Q4 | 20 tok/s |
| Llama 13B Q4 | VRAM N/A |
| Llama 30B Q4 | VRAM N/A |
| Llama 70B Q4 | Offload or multi-GPU |
| Stable Diffusion 512px | 12s / img |
| Whisper Large RTF | 1.4x |
RTF < 1.0 = faster than real time. For Stable Diffusion and Whisper lower is better; for tokens/s higher is better.
Compare GTX 1660 Super with another GPU
Is an upgrade worth it? Compare specs and real benchmarks side by side.
Open comparator →Compatible AI Models — GTX 1660 Super
44 models run fully in VRAM · 13 with CPU offloading
Whisper Large V3
Stable Diffusion 3.5 Medium
Stable Diffusion 3 Medium
Stable Diffusion XL
DeepSeek R1 Distill 8B
Qwen3.5 9B
Qwen3 8B
Qwen2.5-Coder 7B
Show all 44 compatible models →
Also runs with CPU offloading (13)
- Phi-4 4.2 GB Q2 How to install →
- DeepSeek R1 Distill 14B 4.2 GB Q2 How to install →
- Gemma 4 12B 3.3 GB Q2 How to install →
- Qwen2.5 14B 4.2 GB Q2 How to install →
- DeepSeek Coder V2 5 GB Q2 How to install →
- Qwen2.5 Coder 14B 4 GB Q2 How to install →
- Qwen3 14B 3.9 GB Q2 How to install →
- Gemma 3 12B 3.6 GB Q2 How to install →
- Phi-3 Medium 4.5 GB Q2 How to install →
- StarCoder 2 15B 4.5 GB Q2 How to install →
- Mistral Nemo 12B 3.5 GB Q2 How to install →
- DeepSeek V2 Lite 5 GB Q2 How to install →
- Llama 3.2 11B Vision 3.3 GB Q2 How to install →
GTX 1660 Super · Amazon
Os precos de GPU mudam com frequencia entre lojas. Consulte a oferta atual antes de comprar.
Ver oferta atualAlguns links são links de afiliado da Amazon. Podemos receber uma comissão sem custo adicional para si. O cookie da Amazon pode durar até 24 horas após o clique.
GTX 1660 Super for Local AI
La GTX 1660 Super con 6GB de GDDR6 puede correr modelos de IA locales pequeños en cuantización agresiva. Con Q4 o Q2 puedes ejecutar modelos Phi-3 Mini, Gemma 3 4B y algunos modelos 7B pequeños. Es una opción de entrada para explorar IA local con hardware existente.
Los benchmarks de GTX 1660 Super muestran 20 tokens/segundo en modelos 7B Q4. Whisper para transcripción de audio funciona bien en todos sus tamaños. Para generación de imágenes, Stable Diffusion 3 Medium encaja en esta VRAM.
Para maximizar los modelos que puedes correr con esta GPU, consulta la calculadora de VRAM. Si necesitas más capacidad, revisa nuestra guía para elegir GPU para IA local.
Plan your full AI build
GTX 1660 Super · 6 GB VRAM — configure PSU, RAM, storage and check compatible models.
Related articles
Not sure which model to run on your GTX 1660 Super?
The VRAM calculator tells you exactly which quantization you need.
Get the best price for GTX 1660 Super
Open Amazon with our affiliate link and check availability, variants, and current deals.