NVIDIA RTX 4070 Super - 12GB usable

Specifications

BrandNVIDIA
ModelRTX 4070 Super
Usable VRAM12GB
ArchitectureAda
CUDA / Stream Processors7,168
Memory Bandwidth504 GB/s
TDP220W
FP32 TFLOPS36

Current Offers

Used from 550

Prices last updated:

GPUDojo is reader-supported. When you buy through links on our site, we may earn an affiliate commission.

Price History

  • eBay550at high
Mar 13Apr 17May 22Jul 3Aug 7Sep 4510550

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: ~38 tokens/sec

Prefill: ~643 tokens/sec

Recommended Quantisations

  • Q4_K_M for 14B (tight fit)
  • Q6_K or Q8 for 7B models

Pros & Cons

Pros

  • Ada architecture: broad CUDA software support
  • Consumer card: easy to install, display output

Cons

  • 12GB 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 Super. Know a good review? Let us know.