Back to Models

Lfm2.5 350M

Text Generation

Liquid LFM2.5 350M - hybrid conv+attention LLM optimized for edge deployment (9 languages, tool calling)

Integration

main.rs
use xybrid_sdk::{Xybrid, Envelope};

// Load the LLM
let model = Xybrid::model("lfm2.5-350m").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
Liquid
Parameters
354M
Format
gguf
Quantization
q4_k_m
Size
254.7 MB
Model ID
lfm2.5-350m