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
Used from £160
Prices last updated:
GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.
Lowest tracked offers by retailer
UK · GBP · Weekly since Aug 2026 · Shipping may be extra
- eBay £160 mid-range
About these prices
Each line is the lowest offer we tracked from that retailer at weekly snapshots, ending at today's offer. The condition can vary between snapshots (new, used, or unrecorded for older ones). eBay prices exclude shipping.
Weekly offers table
| Date | eBay |
|---|---|
| Today, Nov 3, 2026 | £160.00 |
| Oct 30, 2026 | £160.00 |
| Oct 23, 2026 | £156.70 |
| Oct 9, 2026 | £175.00 |
| Oct 2, 2026 | £151.50 |
| Sep 25, 2026 | £155.66 |
| Sep 18, 2026 | £167.09 |
| Sep 11, 2026 | £146.30 |
| Sep 1, 2026 | £146.30 |
| Aug 28, 2026 | £145.26 |
| Aug 21, 2026 | £120.00 |
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.