🚀 Local multi-LLM testing & performance tracker
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 12 nodes and runs when a chat message arrives. Along the way it connects OpenAI Chat Model and Google Sheets. It also calls 0.0.0.0:1234 over HTTP.
How it runs
Trigger: When a chat message arrives.
- Get Models (HTTP Request): calls 0.0.0.0:1234
- Extract Model IDsto Run Separately (Split Out): splits a list into separate items
- Capture Start Time (Date & Time): formats or calculates dates
- Add System Prompt (Edit Fields (Set)): sets 1 field: system_prompt
- LLM Response Analysis (Basic LLM Chain): sends a prompt to an LLM, with model: Run Model with Dunamic Inputs
- Capture End Time (Date & Time): formats or calculates dates
- Get timeDifference (Date & Time): formats or calculates dates
- Prepare Data for Analysis (Edit Fields (Set)): sets 6 fields: llm_response, prompt, model…
- Analyze LLM Response Metrics (Code): runs custom JavaScript code
- Save Results to Google Sheets (Google Sheets): append
Services it uses
HTTP calls to: 0.0.0.0:1234
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (9)
- HTTP Request
n8n-nodes-base.httpRequest - Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - Date & Time
n8n-nodes-base.dateTime - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Code
n8n-nodes-base.code - Google Sheets
n8n-nodes-base.googleSheets - Edit Fields (Set)
n8n-nodes-base.set - Split Out
n8n-nodes-base.splitOut - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm
From the author
🚀 Local Multi-LLM Testing & Performance Tracker This workflow is perfect for developers, researchers, and data scientists benchmarking multiple LLMs with LM Studio. It dynamically fetches active models, tests prompts, and tracks metrics like word count,…