NVIDIA GTX 1660 Super GPU: Specs, VRAM, Price & Benchmarks (2026)
The GTX 1660 Super is a real GPU (launched 2019), but no provider on Aquanode is listing it for rental right now, so there is no live hourly price to quote. Availability changes as providers add and retire hardware; the specs, VRAM and price context below still apply.
How much VRAM does the GTX 1660 Super have?
The GTX 1660 Super has 6GB GDDR6, with 336 GB/s of derived memory bandwidth (bus width × transfer rate; not a vendor-stated figure).
GTX 1660 Super VRAM calculator: check which models fit in its memory at each precision.
What can the GTX 1660 Super run?
Popular open models from small to frontier scale, with the memory each needs and how many GTX 1660 Super cards (6GB GDDR6 each) that takes.
| Model | As published | FP8 | INT4 |
|---|---|---|---|
| Qwen/Qwen3-8B 8.2B | BF16: not supported | FP8: not supported | INT4: ~4.6 GB, 1 GPU |
| Qwen/Qwen2.5-14B-Instruct 14.8B | BF16: not supported | FP8: not supported | INT4: ~8.3 GB, 2 GPUs |
| Qwen/Qwen3-32B 32.8B | BF16: not supported | FP8: not supported | INT4: ~18.3 GB, 4 GPUs |
| Qwen/Qwen-72B 72.3B | BF16: not supported | FP8: not supported | INT4: ~40.4 GB, 7 GPUs |
| MiniMaxAI/MiniMax-M2.7 228.7B | FP8: not supported | – | INT4: ~128 GB, 22 GPUs |
| deepseek-ai/DeepSeek-R1 684.5B | FP8: not supported | – | INT4: ~383 GB, 64 GPUs |
Estimates: weights at the stated precision plus a flat 20% for KV cache and overhead, at a moderate context length. A dash means the precision is not offered for that model (it is already published at that size). INT4 needs a published quantized checkpoint. Open any model for a per-GPU breakdown, or use the GTX 1660 Super VRAM calculator.
GTX 1660 Super specs
| Architecture | launched 2019 |
| VRAM | 6GB GDDR6 |
| Memory bandwidth | 336 GB/s |
| TDP | 125W |
| Form factor | PCIe |
Specs sourced from the vendor's public product page. See the source.
GPU Glossary: What is VRAM?, Tensor Cores, CUDA Cores, TFLOPS
Good for
The smallest card on this list: 6GB for 3B models at FP16 and 7B models at aggressive INT4, plus embeddings, speech and small vision models.
Not good for
No tensor cores at all, no BF16 or FP8, and 6GB. A 7-8B model at INT4 leaves almost nothing for context.
Related guides
Other models in the same generation. The full list is in the GPU index.
Get notified when the price drops
GPU supply moves hourly. Tell us what you're waiting for and we'll email you when a matching offer appears across any provider we track.
