Machete DGX
For NVIDIA DGX Spark

Your DGX Spark,
in your pocket.

Live GPU telemetry, a real SSH terminal, Docker control, chat with your own local LLM and one-tap model downloads — everything your Spark does, on the phone in your hand.

iPhone & iPad · Android coming · 9 languages · connects over SSH on your own network

Live dashboard
Live dashboard
What's loaded in GPU
What's loaded in GPU
SSH terminal
Full SSH terminal
Docker
Docker control
Local LLM chat
Chat with your LLM
Hugging Face models
Hugging Face models
Training
Training progress
Benchmark
Throughput benchmark
Energy cost
Energy cost
Alerts
Smart alerts
Image generation
Image generation
Backups
Scheduled backups

What it does

Everything your Spark does — live.

Machete talks to your machine over SSH on your own network. No cloud in the middle, no agent required to get started.

📊

Live GPU dashboard

Utilisation, temperature, power draw, unified memory, disk and network — sampled continuously, with history charts and a clear marker when data goes stale.

🧠

See what's in VRAM

Every process resident in GPU memory, with its footprint and endpoint — and one tap to unload a model and free the memory.

⌨️

Real SSH terminal

A proper xterm session with a key toolbar, not a command box. Paste, scroll, Ctrl-combos.

🐳

Docker control

Containers and images with live CPU, memory and per-container GPU usage. Start, stop, restart, inspect logs.

💬

Chat with your own LLM

Any OpenAI-compatible endpoint on your Spark — vLLM, llama.cpp. Streamed replies, model picker, throughput benchmark.

📦

Hugging Face, one tap

Search the hub, download straight to the Spark with resumable multi-connection transfers, then serve it with a saved run config.

🎓

Training at a glance

Finds your running fine-tune, plots the loss curve, estimates time left and what the run has cost in electricity.

🔔

Alerts that matter

Thresholds on any metric, plus training finished, training stalled and loss targets — delivered as notifications.

💾

Scheduled backups

Configs, Docker volumes and any path you choose, on a schedule, to the cloud storage you already use.

Machete Pro

Monitoring is free. The controls are Pro.

The live dashboard, GPU telemetry and history stay free forever. A Pro subscription unlocks everything that reaches into the machine.

  • Full SSH terminal
  • Docker control
  • Local LLM chat
  • Model downloads
  • Image generation
  • Training panel
  • Automation & backups
  • Multiple servers
  • GPU unload & executive actions

Monthly or yearly, billed through the App Store. Cancel any time in your account settings — cancellation takes effect at the end of the current period.