NVIDIA RTX 3080 Ti - 12GB usable
Specifications
| Brand | NVIDIA |
|---|---|
| Model | RTX 3080 Ti |
| Usable VRAM | 12GB |
| Architecture | Ampere |
| CUDA / Stream Processors | 10,240 |
| Memory Bandwidth | 912 GB/s |
| TDP | 350W |
| FP32 TFLOPS | 34 |
Current Offers
Used from £500
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 £500 at 90-day high
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 | £500.00 |
| Oct 30, 2026 | £500.00 |
| Oct 23, 2026 | £491.20 |
| Oct 9, 2026 | £419.00 |
| Oct 2, 2026 | £414.70 |
| Sep 25, 2026 | £414.70 |
| Sep 18, 2026 | £450.40 |
| Sep 11, 2026 | £440.20 |
| Sep 1, 2026 | £399.40 |
| Aug 28, 2026 | £399.40 |
| Aug 21, 2026 | £363.70 |
For AI / LLM Use
Entry-level for local AI. Handles 7B-8B models well.
What Models Can It Run?
- 14B Q4_K_M, 7B full precision
- 7B Q6_K, 14B Q3_K (tight)
- 7B Q4_K_M only
Estimated Performance
Generation: ~68 tokens/sec
Prefill: ~607 tokens/sec
Recommended Quantisations
- Q4_K_M for 14B (tight fit)
- Q6_K or Q8 for 7B models
Pros & Cons
Pros
- High memory bandwidth for fast generation
- Ampere architecture: broad CUDA software support
- Consumer card: easy to install, display output
Cons
- 12GB usable VRAM: may need quantization for 30B+ models
- 350W TDP: high power draw
Community Verdict
No community reviews yet for the RTX 3080 Ti. Know a good review? Let us know.