NVIDIA RTX 2060 Super - 8GB usable
8GB Turing with tensor cores, so prompts process far quicker than on any Pascal card. 8GB is the hard limit on what you can load.
Specifications
| Brand | NVIDIA |
|---|---|
| Model | RTX 2060 Super |
| Usable VRAM | 8GB |
| Architecture | Turing |
| CUDA / Stream Processors | 2,176 |
| Memory Bandwidth | 448 GB/s |
| TDP | 175W |
| FP32 TFLOPS | 7.2 |
Current Offers
Used from €160
Prices last updated:
GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.
Price History
- eBay€160at high
For AI / LLM Use
Limited VRAM restricts you to 7B quantized models.
What Models Can It Run?
- 7B Q6_K, 14B Q3_K (tight)
- 7B Q4_K_M only
Estimated Performance
Generation: ~34 tokens/sec
Prefill: ~129 tokens/sec
Recommended Quantisations
- Q4_K_M for 7B models
- Q3_K for larger experiments
Pros & Cons
Pros
- Turing architecture: broad CUDA software support
- Consumer card: easy to install, display output
Cons
- Only 8GB usable VRAM: limited to small models
- Moderate memory bandwidth: not the fastest for inference
Community Verdict
No community reviews yet for the RTX 2060 Super. Know a good review? Let us know.