InferX — Serverless GPU Inference Platform for Production Workloads

Tenant Namespace Pod Name State Node Name Req. GPU Count Req. GPU vRam (MB) Type Standby (MB) Allocated GPU vRam (MB) Allocated GPU Slots
GPU Pageable Pinned GPU Slot Count
public ActionAnalytics public/ActionAnalytics/CR-70B/54/94 Standby computeinstance-e00r2jrqynf83a8b4f 4 71000 Restore Mem : 271616 File : 5464 File : 4 0 N/A
public Qwen public/Qwen/IntelliAsk-Qwen3-32B-450-Merged/76/86 Snapshoting computeinstance-e00r2jrqynf83a8b4f 2 58000 Snapshot Mem : 0 File : 0 File : 0 58112 0 227
3 227
public Trial public/Trial/Huihui-Qwen3-Next-80B-A3B-Thinking-abliterated/87/93 Loading computeinstance-e00r2jrqynf83a8b4f 4 45000 Snapshot File : 0 File : 0 File : 0 45056 1 176
2 176
4 176
5 176
public Trial public/Trial/L3.3-70B-Loki-V2.0/66/81 Loading computeinstance-e00r2jrqynf83a8b4f 2 71000 Snapshot File : 0 File : 0 File : 0 71168 6 278
7 278