NVIDIA RTX 2070 Super - 8GB usable
The sensible 8GB Turing pick, quicker than the 2060 Super. Still 8GB, so it runs 7B comfortably and little beyond.
Specifications
| Brand | NVIDIA |
|---|---|
| Model | RTX 2070 Super |
| Usable VRAM | 8GB |
| Architecture | Turing |
| CUDA / Stream Processors | 2,560 |
| Memory Bandwidth | 448 GB/s |
| TDP | 215W |
| FP32 TFLOPS | 9 |
Current Offers
New from $235
Prices last updated:
GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.
Price History
- Amazon$235current
- Newegg$745at 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: ~161 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 2070 Super. Know a good review? Let us know.