A description (tagline) is not available for this product.
AI inference · LLM serving · 8K rendering
AI inference · LLM serving · 8K rendering
IPMI/iDRAC · 100 GB free backup · Native IPv6 · IPv4 /29 on request
AI inference (up to 32 B params), Stable Diffusion / Flux, Blender / Octane, 4K live encoding
Manual setup, ~24 hours after payment. Welcome email contains IPMI credentials, root password, and the OS/framework you selected pre-installed.
Best for inference
IPMI/iDRAC · 100 GB free backup · Native IPv6 · IPv4 /29 on request
Llama-3.1 70B / Qwen-72B in a single card, large-batch fine-tuning, 8K render, multi-stream AI transcoder
Manual setup, ~24 hours after payment. Welcome email contains IPMI credentials, root password, and the OS/framework you selected pre-installed.
Flagship · 70B in one card