Back to Models
Ministral 3 3B
Text GenerationMinistral 3 3B Instruct - Mistral AI's edge-optimized instruction-tuned LLM with 256K context
Integration
main.rs
use xybrid_sdk::{Xybrid, Envelope};
// Load the LLM
let model = Xybrid::model("ministral-3-3b").load()?;
// Run text generation
let result = model.run(&Envelope::text("Explain quantum computing in simple terms."))?;
println!("{}", result.text.unwrap());Details
- Task
- Text Generation
- Family
- Mistral
- Parameters
- 3.4B
- Format
- gguf
- Quantization
- q4_k_m
- Size
- 2.0 GB
- Model ID
- ministral-3-3b