Checkout our live demo – https://aifindx.com
48GB Workstation:
- High Performance Entry Level AI Workstations (10+ Tokens per second w/ 65B Model in 4bit mode)
- Dual RTX-3090s w/ 24GB Each
- NVLINK Connected GPU’s
- 1600w PSU
- High-airflow Optimized mid-tower ATX Case
- 2TB NVME
- Ubuntu 22.04
- Pre-loaded with opensource AI solutions
- Models:
- llama-65b-4bit-128g
- alpaca-30b-lora-int4
- llama-30b-4bit-128g
- MetaIX_GPT4-X-Alpasta-30b-4bit
- Easily download any model from huggingsface
- $5799
- https://openmentis.ai/product/openmentis-48gbvram-128gb/
96GB AI Server:
- High Performance Entry Level AI Server (10+ Tokens per second w/ 65B Model in 4bit mode)
- Dual A6000s w/ 48GB Each
- NVLINK Connected GPU’s
- 1600w PSU
- High-airflow Optimized mid-tower ATX Case
- 2TB NVME
- Ubuntu 22.04
- Pre-loaded with opensource AI solutions
- Models:
- llama-65b-4bit-128g
- alpaca-30b-lora-int4
- llama-30b-4bit-128g
- MetaIX_GPT4-X-Alpasta-30b-4bit
- Easily download any model from huggingsface
- $10999
- https://openmentis.ai/product/openmentis-a6000-96gbvram-128gb/https://openmentis.ai/product/openmentis-a6000-96gbvram-128gb/
Image Generation:
