NVIDIA Titan V - 12GB usable

12GB of HBM2 with Volta tensor cores, unusually quick per gigabyte. Capacity is the ceiling at roughly 13B, and drivers are fading.

Specifications

BrandNVIDIA
ModelTitan V
Usable VRAM12GB
ArchitectureVolta
CUDA / Stream Processors5,120
Memory Bandwidth653 GB/s
TDP250W
FP32 TFLOPS14.9

Current Offers

Used from $450New from $857

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

US · USD · Weekly since May 2026 · Shipping may be extra

  • eBay $450 at 90-day high
  • Amazon $857 current
  • Newegg (no current offer)
$0$250$500$750$1,000$1,250May 8Jun 21Aug 5Sep 19Nov 3Amazon $857Newegg $669eBay $450
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. Tax is excluded. Amazon shows a current price only.

Weekly offers table
Lowest tracked offer per retailer · US · USD
DateeBayAmazonNewegg
Today, Nov 3, 2026 $450.00$856.99–
Oct 30, 2026 $450.00––
Oct 23, 2026 $450.00––
Oct 9, 2026 $399.97––
Oct 2, 2026 $229.00–$669.00
Sep 25, 2026 $229.00–$669.00
Sep 18, 2026 $229.00–$669.00
Sep 11, 2026 $229.00–$669.00
Sep 4, 2026 $229.00–$669.00
Sep 1, 2026 $229.00–$1,249.00
Aug 28, 2026 $229.00–$1,249.00
Aug 21, 2026 $229.00–$1,249.00
Aug 14, 2026 $229.00–$1,249.00
Aug 7, 2026 $229.00–$1,249.00
Jul 31, 2026 $229.00–$1,249.00
Jul 24, 2026 $229.00–$1,249.00
Jul 17, 2026 $229.00–$1,249.00
Jul 10, 2026 $229.00–$1,249.00
Jul 3, 2026 $229.00–$1,249.00
Jun 26, 2026 $229.00–$1,249.00
Jun 19, 2026 $229.00–$1,249.00
Jun 12, 2026 $229.00–$1,249.00
Jun 5, 2026 $229.00–$1,249.00
May 29, 2026 $229.00–$1,249.00
May 22, 2026 $229.00–$1,249.00
May 15, 2026 $229.00–$1,249.00
May 8, 2026 $298.00–$699.00

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: ~49 tokens/sec

Prefill: ~266 tokens/sec

Recommended Quantisations

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

Pros & Cons

Pros

  • Volta 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 Titan V. Know a good review? Let us know.