NVIDIA RTX 4070 Ti Super - 16GB usable
Specifications
| Brand | NVIDIA |
|---|---|
| Model | RTX 4070 Ti Super |
| Usable VRAM | 16GB |
| Architecture | Ada |
| CUDA / Stream Processors | 8,448 |
| Memory Bandwidth | 672 GB/s |
| TDP | 285W |
| FP32 TFLOPS | 44 |
Current Offers
Used from $800New from $1000
Prices last updated:
GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.
Price History
- eBay$800at high
- Amazon$850current
- Newegg$1260mid-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: ~50 tokens/sec
Prefill: ~786 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
- Ada architecture: broad CUDA software support
- Consumer card: easy to install, display output
Cons
- 16GB usable VRAM: may need quantization for 30B+ models
- Moderate memory bandwidth: not the fastest for inference
Community Verdict
No community reviews yet for the RTX 4070 Ti Super. Know a good review? Let us know.