Testing Multiple Local LLMs with LM Studio
detail.loadingPreview
This workflow allows you to test multiple local Large Language Models (LLMs) using LM Studio.
🚀Ready to Deploy This Workflow?
About This Workflow
Overview
This n8n workflow is designed to help you test and compare multiple Large Language Models (LLMs) hosted locally via LM Studio. It facilitates the setup, configuration, and execution of tests against different models, providing insights into their performance based on various parameters and prompts. The workflow includes steps for identifying available models, setting up the environment, configuring LLM parameters like temperature and top P, and optionally logging results to a Google Sheet. It also provides guidance on readability scores and prompt engineering for standardized testing.
Key Features
- Connect to and retrieve models from a local LM Studio server.
- Configure LLM parameters such as temperature, top P, and presence penalty.
- Utilize system prompts to guide model responses for specific testing criteria (e.g., conciseness, readability).
- Calculate and analyze text readability scores and other text metrics.
- Optionally log test results to a Google Sheet for detailed analysis.
- Provides detailed setup instructions and explanations for each node.
How To Use
- Set up LM Studio: Download and install LM Studio. Load the desired LLM models into the LM Studio server.
- Update Workflow Credentials: In the n8n workflow, locate the
Get Modelsnode. Update theWEBHOOK_URLenvironment variable to match the IP address and port of your LM Studio server. - Configure LLM Settings: Adjust the
Temperature,Top P, andPresence Penaltyparameters in theRun Model with Dunamic Inputsnode to fine-tune model behavior. - Define System Prompt: Utilize the
Sticky Notenode at560, -160to define a system prompt that guides the LLM's responses according to your testing criteria (e.g., readability, conciseness). - Optional: Google Sheet Integration: If you wish to log results, create a Google Sheet with the specified headers and update the corresponding Google Sheets node in the workflow.
- Execute the Workflow: Trigger the workflow manually or via a webhook to begin testing your local LLMs.
Apps Used
Workflow JSON
{
"id": "e50f1411-83fe-4f35-ab3c-171e6f35f318",
"name": "Testing Multiple Local LLMs with LM Studio",
"nodes": 0,
"category": "LLM Automation",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: e50f1411-83fe...
About the Author
Crypto_Watcher
Web3 Developer
Automated trading bots and blockchain monitoring workflows.
Statistics
Verification Info
Related Integrations
- Gmail + Schedule Trigger(270 workflows)
- Gmail + Google Sheets(245 workflows)
- Gmail + Split Out(132 workflows)
- Gmail + Gmail Trigger(119 workflows)
- Form Trigger + Gmail(107 workflows)
- Gmail + Google Drive(93 workflows)
- Airtable + Schedule Trigger(86 workflows)
- Gmail Trigger + Google Sheets(71 workflows)
- Gmail + Telegram(63 workflows)
- Gmail + Slack(59 workflows)
Related Workflows
Discover more workflows you might like
Automate Event Attendee Data Extraction with AI-Powered Scraping
This n8n workflow leverages AI and Bright Data's MCP to automate the scraping of event attendee, venue, and feedback data from 10times.com. Schedule the extraction to run daily and automatically save the organized data to Google Sheets.
Automated Multi-Platform Social Media Publisher
Streamline your social media content creation and publishing with this n8n workflow. Simply fill out a web form with your caption, media (image or video), and target platforms, and let n8n automate the posting process across multiple social networks.
Automate Local Business Outreach with AI-Powered Yelp Scraper
This workflow automates the process of scraping local business details from Yelp using AI, then leverages that data to send personalized partnership proposals via Gmail. It's perfect for sales and marketing teams looking to streamline lead generation and outreach campaigns.
AI-Powered PostgreSQL Data Agent with Conversational Interface
This n8n workflow empowers you to build an intelligent, conversational agent for your PostgreSQL database. Interact with your data using natural language, perform CRUD operations, explore schemas, and generate dynamic visualizations, streamlining data management and access for any user.
Smart Expense Tracking with Telegram & AI
Automate your personal finance management by turning your Telegram chat into an intelligent expense tracker. Simply send a photo of a receipt or a text message, and this workflow uses AI to categorize your spending, extract crucial details, and provide instant summaries.
AI-Powered YouTube Video Metadata Automation
Effortlessly optimize your YouTube videos for search and engagement. This workflow automates the generation of SEO-friendly titles, descriptions, tags, and hashtags using AI, directly updating your YouTube content based on video transcripts and focus keywords.