🚀 LM Studio Cluster Admin Panel

Production-ready distributed inference cluster

API Server

—

Workers

—

API Keys

—

Today's Tokens

—

Cluster Overview

Registered Workers

Status

Select workers, then load the current default model.

LM Studio Runtime Settings (Bulk)

Saved once and reused when loading models on any node.

Context Length

Eval Batch Size

Num Experts

Acceleration Toggles

Flash Attention Offload KV Cache to GPU

Advanced Settings (JSON)

Any extra LM Studio load fields go here and are applied cluster-wide.

Download on All Nodes

Use a Hugging Face model URL. The same download command is sent to every online worker.

Per-Node Model Selector

Default Model for Cluster

Add New API Key

Key (API Key)

User Name

Tier

Max Requests/sec

Existing Keys

Inference Playground

API Key

Model (Optional)

Prompt

Max Tokens

API Server Logs (Last 100 lines)

🐒 Code Monkey Token Usage

Total Requests

—

All-time Prompt Tokens

—

All-time Completion Tokens

—

Today's Requests

—

Worker	Host	Requests	Prompt Tokens	Completion Tokens