About

Overview

Performance

  • 120B MoE inference: Up to 115 tokens/s
  • Token generation at 115 tokens/s:
    • 414,000 tokens/hour
    • 9.94 million tokens/day
    • 298 million tokens/month at continuous utilization
  • SDXL image generation: 1.25 seconds per 1024×1024 image at 20 steps
  • Video generation: Production-ready 5-second 720p clips
  • Total GPU memory: 96 GB

Cost Savings

For teams spending $2,000+ per month on AI and approximately $2,500 per month on Sonnet, Opus, image, and video generation, this workstation moves recurring workloads to controlled, local infrastructure.

  • Paid off in 10 months
  • Save $46,259 over three years
  • Save $154,259 over five years
Characteristics
GPU 2x RTX PRO 5000 Blackwell
CPU Intel Xeon 658X Enterprise (24 Cores)
Board ASUS Pro WS W890E-SAGE SE
VRAM 96GB GDDR7
System RAM 128GB DDR5 ECC 6400
Storage 2TB Enterprise SSD + 2TB HDD
Power 1700W Titanium
Cooling Air-cool GPUs · Liquid-Cool CPU
Overview

Performance

  • 120B MoE inference: Up to 115 tokens/s
  • Token generation at 115 tokens/s:
    • 414,000 tokens/hour
    • 9.94 million tokens/day
    • 298 million tokens/month at continuous utilization
  • SDXL image generation: 1.25 seconds per 1024×1024 image at 20 steps
  • Video generation: Production-ready 5-second 720p clips
  • Total GPU memory: 96 GB

Cost Savings

For teams spending $2,000+ per month on AI and approximately $2,500 per month on Sonnet, Opus, image, and video generation, this workstation moves recurring workloads to controlled, local infrastructure.

  • Paid off in 10 months
  • Save $46,259 over three years
  • Save $154,259 over five years
Characteristics
GPU 2x RTX PRO 5000 Blackwell
CPU Intel Xeon 658X Enterprise (24 Cores)
Board ASUS Pro WS W890E-SAGE SE
VRAM 96GB GDDR7
System RAM 128GB DDR5 ECC 6400
Storage 2TB Enterprise SSD + 2TB HDD
Power 1700W Titanium
Cooling Air-cool GPUs · Liquid-Cool CPU
SMTTR - Standard Matter by SMTTR - Standard Matter

SMTTR ONE 96GB VRAM Nvidia Blackwell AI Workstation

Regular price
$19,917.00
Sale price
$19,917.00
Regular price
FREE Delivery on Orders $3,000+
* NO SALES TAX Except in CA
** Prices and stock might change without notice due to high market volatility.
Run 120B MoE models at up to 115 tokens/s, generate SDXL images in 1.25 seconds, and produce 5-second 720p video clips locally. ...  Read more
Run 120B MoE models at up to 115 tokens/s, generate SDXL images in 1.25 seconds, and produce 5-second 720p video clips locally. The workstation pays for itself in 10 months, saving $46,259 over three years and $154,259 over five years.

Condition: New, Factory-Sealed

Request Personalized Corporate Quote - Get Up To 5% OFF on Volume!

Warranty & Support
Covered under a 3-YEAR EXTENDED WARRANTY from the manufacturer & SMTTR.
Shipping & Fulfillment
All products ship from verified U.S. distributors or SMTTR testing facility
Returns & Refunds
Returns accepted within 30 days Learn more

Shop with confidence! SMTTR is an authorized SMTTR - Standard Matter Partner Reseller

Let customers speak for us

WHY CHOOSE SMTTR

AI Solutions & Hardware Powered by NVIDIA Certified Professionals

TRUSTED BY

ENGINEERS FROM LEADING COMPANIES & OUR PARTNERS