Llama Prompt Guard 2 22M Onnx
Open Weights • Released 2025-05-20 • Last Verified 2026-08-06
Llama Prompt Guard 2 22M Onnx is a high-dimensional text embedding and semantic retrieval model developed by Gravitee Io. Tailored for Retrieval-Augmented Generation (RAG), vector database indexing, semantic similarity matching, and cross-lingual passage re-ranking.
Plain English Summary (What is this model & who is it for?)
Think of Llama Prompt Guard 2 22M Onnx as a versatile AI assistant for writing, research, and brainstorming. It helps you draft emails, write essays, summarize long articles, and generate creative ideas on any topic.
💡 Real-World Use Cases & Practical Examples
🚀 How to Run & Use This Model (Step-by-Step Guide)
Simple setup instructions for everyday users and developers.
Download a One-Click App (No Coding Required)
Download a free local AI launcher like LM Studio (lmstudio.ai) or Ollama (ollama.com) on your Mac, Windows, or Linux PC.
Load the Model
In LM Studio, search for "Llama Prompt Guard 2 22M Onnx". In Ollama, open your terminal and run "ollama run gravitee-io-llama-prompt-guard-2-22m-onnx".
Start Chatting or Generating
Type your text instructions or upload files into the app. The AI runs 100% privately on your hardware without internet requirement!
Developer API Integration
Developers can integrate Llama Prompt Guard 2 22M Onnx directly via Python (using Hugging Face transformers/diffusers) or connect via local OpenAI-compatible REST server (http://localhost:11434).
Benchmark Performance
Hardware Requirements for Local Running
Consumer GPU / CPU compatible
Strengths
- •Strong Instruction Following & Alignment
- •Multi-Turn Dialogue Context Stability
- •Low-Latency Batch Inference Execution
- •Support for Structured JSON & Schema Enforcing
Limitations & Weaknesses
- •Requires local GPU hardware for self-hosting
import openai
client = openai.OpenAI()
response = client.chat.completions.create(
model="gravitee-io-llama-prompt-guard-2-22m-onnx",
messages=[
{"role": "system", "content": "You are an expert AI assistant."},
{"role": "user", "content": "Explain quantum computing in 2 sentences."}
]
)
print(response.choices[0].message.content)Pricing Overview
Prices subject to provider tiers and volume discounts. Check documentation for current token rates.
Model Tags
Similar Models from Gravitee Io
Distilbert Multilingual Toxicity Classifier
Open Weights
Distilbert Multilingual Toxicity Classifier is a high-dimensional text embedding and semantic retrieval model developed by Gravitee Io. Tailored for Retrieval-Augmented Generation (RAG), vector database indexing, semantic similarity matching, and cross-lingual passage re-ranking.
Bert Small Toxicity
Open Weights
Bert Small Toxicity is a high-dimensional text embedding and semantic retrieval model developed by Gravitee Io. Tailored for Retrieval-Augmented Generation (RAG), vector database indexing, semantic similarity matching, and cross-lingual passage re-ranking.
Detoxify Onnx
Open Weights
Detoxify Onnx is a high-dimensional text embedding and semantic retrieval model developed by Gravitee Io. Tailored for Retrieval-Augmented Generation (RAG), vector database indexing, semantic similarity matching, and cross-lingual passage re-ranking.