Testing Multiple Local LLMs with LM Studio
detail.loadingPreview
This workflow allows you to test and compare multiple local LLMs hosted via LM Studio, providing insights into their responses and performance.
🚀Ready to Deploy This Workflow?
About This Workflow
Overview
This n8n workflow is designed to facilitate testing of multiple Large Language Models (LLMs) hosted locally using LM Studio. It guides users through the setup process, including updating the LM Studio server URL, configuring LLM settings, and optionally creating a Google Sheet to log test results. The workflow fetches available models, allows for dynamic input and testing, and can measure response times and analyze text characteristics like readability.
Key Features
- Connect to and query local LLM models hosted via LM Studio.
- Dynamically select and run specific models for testing.
- Configure LLM parameters such as temperature, top P, and presence penalty.
- Measure response times between sending a prompt and receiving a completion.
- Analyze generated text for readability scores, word length, word count, and sentence count (requires additional nodes not fully detailed in snippet).
- Optional logging of test results to a Google Sheet.
How To Use
- Setup LM Studio: Download, install, and run LM Studio. Load the desired LLM models.
- Update Workflow URL: In the n8n workflow, update the
WEBHOOK_URLenvironment variable or the relevant node parameter to point to your LM Studio server's base URL (e.g.,http://localhost:1234). - Get Models: Run the 'Get Models' node (HttpRequest) to fetch a list of available LLMs from your LM Studio server.
- Configure LLM Settings: Adjust parameters like 'Temperature', 'Top P', and 'Presence Penalty' in the LLM interaction nodes as needed for your testing.
- Define Prompts: Prepare your prompts, potentially including system prompts to guide model behavior.
- Run Tests: Execute the workflow to send prompts to selected models and receive responses.
- Analyze Results: Utilize additional nodes (like text analysis or Google Sheets integration) to log and analyze the generated outputs.
Apps Used
Workflow JSON
{
"id": "0028ff04-2959-49ad-bc4d-bde2eac8cb28",
"name": "Testing Multiple Local LLMs with LM Studio",
"nodes": 0,
"category": "AI/LLM",
"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: 0028ff04-2959...
About the Author
SaaS_Connector
Integration Guru
Connecting CRM, Notion, and Slack to automate your life.
Statistics
Verification Info
Related Workflows
Discover more workflows you might like
Ollama Chat Workflow
Integrates Ollama LLM for chat message processing, returning structured JSON responses.
Generate YouTube Video Summaries, Transcripts, and Visual Insights
Automate the extraction of summaries, transcripts, and scene descriptions from YouTube videos.
AI-Powered YouTube Playlist and Video Summarization and Analysis
Summarize and analyze YouTube playlists and individual videos using AI.
Automate Instagram Reel Analysis with Gemini and Apify
Unlock deeper insights into your Instagram Reels by automating analysis. This workflow leverages Apify to fetch reel data and Gemini AI to dissect key elements like background, pose, text, and context, enabling better content replication.
Telegram Profanity & Toxicity Filter
This n8n workflow automatically monitors incoming Telegram messages for profanity and toxic language. It leverages Google's Perspective API to analyze message content, and if a message is deemed inappropriate, the workflow sends an automated warning response back to the sender.
Automate Competitor Tracking with Crunchbase & ClickUp
Streamline competitor analysis by automatically fetching data from Crunchbase and creating review tasks in ClickUp. Stay informed about market changes without manual effort.