logo

InferX AI Function Platform (Lambda Function for Inference)

    --   Serve tens models in one box with ultra-fast (<2 sec) cold start (contact: support@inferx.net)

Action

Models

tenant namespace model name gpu count vram (GB) cpu memory (GB) standby state snapshot nodes revision
gpu pageable pinned
public microsoft Phi-3-mini-128k-instruct 1 13.0 12.0 18.0 Blob Blob Blob Normal ['node2'] 187
public microsoft Phi-3-mini-4k-instruct 1 13.0 12.0 18.0 Blob Blob Blob Normal ['node2'] 185

Summary

Model Count

2

Required GPU Count

2

Required VRAM (GB)

26.0 GB

Required CPU Cores

24.0

Required Memory (GB)

36.0 GB