Smollm2 360M

Text Generation

SmolLM2 360M - HuggingFace's best tiny LLM, excellent quality/size ratio

Integration

main.rs

use xybrid_sdk::{Xybrid, Envelope};

// Load the LLM
let model = Xybrid::model("smollm2-360m").load()?;

// Run text generation
let result = model.run(&Envelope::text("Explain quantum computing in simple terms."))?;

println!("{}", result.text.unwrap());

Variants

Variant	Format	Quantization	Size
universal (default)	gguf	q4_k_m	254.2 MB
web	litertlm	int8	356.4 MB