NVIDIA H100 PCIe - 80GB usable

Specifications

BrandNVIDIA
ModelH100 PCIe
Usable VRAM80GB
ArchitectureHopper
CUDA / Stream Processors14,592
Memory Bandwidth2000 GB/s
TDP350W
FP32 TFLOPS51

Current Offers

Used from $35,999

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 Aug 2026 · Shipping may be extra

  • eBay $35,999 at 90-day high
  • Newegg (no current offer)
$27,500$30,000$32,500$35,000$37,500Aug 21Sep 8Sep 27Oct 15Nov 3eBay $35,999Newegg $29,500
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
DateeBayNewegg
Today, Nov 3, 2026 $35,999.00–
Oct 30, 2026 $35,999.00–
Oct 9, 2026 –$29,500.00
Oct 2, 2026 –$34,989.00
Sep 25, 2026 –$29,500.00
Sep 11, 2026 $27,999.99$34,879.00
Sep 4, 2026 $27,999.99$32,879.00
Sep 1, 2026 $27,999.99$32,879.00
Aug 28, 2026 $27,999.99$32,879.00
Aug 21, 2026 $27,999.99$32,879.00

For AI / LLM Use

Best for running 70B+ models on a single GPU. Very fast generation speed. Datacenter card with no display output, may need aftermarket cooling.

What Models Can It Run?

  • 70B full precision
  • 70B Q4_K_M, 30B full precision
  • 30B Q6_K, 70B Q2_K
  • 30B Q4_K_M, 14B full precision, 70B Q2 (tight)
  • 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: ~150 tokens/sec

Prefill: ~911 tokens/sec

Recommended Quantisations

  • Q6_K or Q8 for best quality
  • Q4_K_M for larger models
  • Full precision for 30B and below

Pros & Cons

Pros

  • 80GB usable VRAM: handles large models
  • High memory bandwidth for fast generation
  • Hopper architecture: broad CUDA software support

Cons

  • 350W TDP: high power draw
  • No display output: headless only
  • May need aftermarket cooling solution

Community Verdict

No community reviews yet for the H100 PCIe. Know a good review? Let us know.