NVIDIA RTX 3080 Ti - 12GB usable

Specifications

BrandNVIDIA
ModelRTX 3080 Ti
Usable VRAM12GB
ArchitectureAmpere
CUDA / Stream Processors10,240
Memory Bandwidth912 GB/s
TDP350W
FP32 TFLOPS34

Current Offers

Used from $560New from $700

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 Mar 2026 · Shipping may be extra

  • eBay $560 mid-range
  • Amazon $700 current
  • Newegg (no current offer)
$250$500$750$1,000$1,250$1,500Mar 13May 12Jul 12Sep 10Nov 10Amazon $700Newegg $699eBay $560
About these prices

Each line is the lowest offer we tracked from that retailer at weekly snapshots, ending at today's offer. A dotted stretch means no offer was recorded in between. 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 10, 2026 $559.99$699.99–
Nov 6, 2026 $559.99––
Oct 30, 2026 $500.00––
Oct 23, 2026 $599.99––
Oct 9, 2026 $520.00––
Oct 2, 2026 $599.95–$699.00
Sep 25, 2026 $489.99–$699.00
Sep 18, 2026 $475.00–$1,240.00
Sep 11, 2026 $450.00–$699.99
Sep 4, 2026 $449.99–$1,289.00
Sep 1, 2026 ––$1,250.00
Aug 28, 2026 ––$699.99
Aug 21, 2026 ––$599.99
Aug 14, 2026 ––$509.99
Aug 7, 2026 ––$599.99
Jul 31, 2026 $450.00–$599.99
Jul 24, 2026 ––$559.99
Jul 17, 2026 $419.90–$598.00
Jul 10, 2026 ––$509.99
Jul 3, 2026 ––$499.99
Jun 26, 2026 ––$499.99
Jun 19, 2026 ––$509.99
Jun 12, 2026 ––$479.99
Jun 5, 2026 ––$598.00
May 29, 2026 ––$599.00
May 22, 2026 ––$509.99
May 15, 2026 ––$599.00
May 8, 2026 ––$1,170.00
May 1, 2026 ––$599.00
Apr 24, 2026 $450.00–$479.99
Apr 17, 2026 ––$1,170.00
Apr 10, 2026 $449.00–$1,170.00
Apr 3, 2026 $350.00–$599.99
Mar 27, 2026 ––$599.99
Mar 15, 2026 ––$1,289.00
Mar 13, 2026 ––$1,289.00

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: ~68 tokens/sec

Prefill: ~607 tokens/sec

Recommended Quantisations

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

Pros & Cons

Pros

  • High memory bandwidth for fast generation
  • Ampere architecture: broad CUDA software support
  • Consumer card: easy to install, display output

Cons

  • 12GB usable VRAM: may need quantization for 30B+ models
  • 350W TDP: high power draw

Community Verdict

No community reviews yet for the RTX 3080 Ti. Know a good review? Let us know.