NVIDIA RTX 5080 - 16GB usable
Specifications
| Brand | NVIDIA |
|---|---|
| Model | RTX 5080 |
| Usable VRAM | 16GB |
| Architecture | Blackwell |
| CUDA / Stream Processors | 10,752 |
| Memory Bandwidth | 960 GB/s |
| TDP | 360W |
| FP32 TFLOPS | 56 |
Current Offers
Used from $1450New from $1580
Prices last updated:
GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.
Price History
- eBay$1450at high
- Amazon$1584current
- Newegg$1580mid-range
For AI / LLM Use
Good for 14B models. 30B requires aggressive quantization.
What Models Can It Run?
- 14B Q6_K, 30B Q3_K (tight)
- 14B Q4_K_M, 7B full precision
- 7B Q6_K, 14B Q3_K (tight)
- 7B Q4_K_M only
Estimated Performance
Generation: ~72 tokens/sec
Prefill: ~1000 tokens/sec
Recommended Quantisations
- Q4_K_M for 14B models
- Q6_K for 7B-8B models
- Q8 for 7B if VRAM allows
Pros & Cons
Pros
- High memory bandwidth for fast generation
- Blackwell architecture: broad CUDA software support
- Consumer card: easy to install, display output
Cons
- 16GB usable VRAM: may need quantization for 30B+ models
- 360W TDP: high power draw
Community Verdict
No community reviews yet for the RTX 5080. Know a good review? Let us know.