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 THUDM chatglm3-6b 1 13.8 12.0 20.0 Blob Blob Blob Normal ['node2'] 160
public THUDM chatglm3-6b-128k 1 13.8 12.0 20.0 Blob Blob Blob Normal ['node2'] 164
public THUDM chatglm3-6b-32k 1 13.8 12.0 20.0 Blob Blob Blob Normal ['node2'] 162

Summary

Model Count

3

Required GPU Count

3

Required VRAM (GB)

41.4 GB

Required CPU Cores

36.0

Required Memory (GB)

60.0 GB