Skip to content
  • Audience: Labs that add a GPU appliance beside the Mac Studio desk
  • Goal: Run LLM API only on Spark; keep Phantom Vision UI/MQTT on Mac
  • Type: Reference

TIP

Mac Studio remains the recommended primary host for Phantom Vision (:5173 / :8788 / :1883) and operator tooling. A DGX Spark (or similar aarch64 GPU box) is an optional second appliance that serves OpenAI-compatible inference only.

Gemma on host(s) only — never on Shadows.


Stack summary

NeedStack
OSUbuntu 24.04 aarch64 (DGX baseline)
GPUCUDA / drivers as NVIDIA ships for the platform
RuntimeDocker + vLLM / NIM
Pairing CGemma 4 26B-class NVFP4 where available
Pairing DNemotron Super / Nano after quality eval
APIOften OpenAI-compat on :8000 (firewall carefully)

Split stack

BoxRole
Mac StudioPhantom Vision UI, MQTT, vms-proxy, Cline, Hermes, SSH to fleet · ≥1 TB storage
SparkLLM HTTP API only; no public bind without auth

Ports to coordinate

  • Spark listen: 8000/tcp (or site standard) for vLLM
  • Mac egress to Spark: that port only
  • Shadows still publish MQTT to Mac :1883, not Spark