NVIDIA GTX 1080 Ti - 11GB usable
11GB and 484 GB/s make this the pick of the Pascal cards, still fine for 7B-13B. Old enough that framework support is lapsing.
Specifications
| Brand | NVIDIA |
|---|---|
| Model | GTX 1080 Ti |
| Usable VRAM | 11GB |
| Architecture | Pascal |
| CUDA / Stream Processors | 3,584 |
| Memory Bandwidth | 484 GB/s |
| TDP | 250W |
| FP32 TFLOPS | 11.3 |
Current Offers
Used from £120
Prices last updated:
GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.
Price History
- eBay£120at high
For AI / LLM Use
Limited VRAM restricts you to 7B quantized models. Older architecture may have limited software support (check CUDA compatibility).
What Models Can It Run?
- 7B Q6_K, 14B Q3_K (tight)
- 7B Q4_K_M only
Estimated Performance
Generation: ~36 tokens/sec
Prefill: ~202 tokens/sec
Recommended Quantisations
- Q4_K_M for 7B models
- Q3_K for larger experiments
Pros & Cons
Pros
- Consumer card: easy to install, display output
Cons
- Moderate memory bandwidth: not the fastest for inference
- Older Pascal architecture: verify current CUDA support
Community Verdict
No community reviews yet for the GTX 1080 Ti. Know a good review? Let us know.