Chuka Josemaria Uzo

Capable Enough to Be Hijacked: Quantization, Caution, and Indirect Prompt Injection in Small Edge LLMs

Small language models are increasingly quantized to run offline on laptops and edge devices, where they often read untrusted documents. This preprint asks whether this compression changes their safety behaviour. We evaluated Qwen2.5-0.5B-Instruct and Qwen2.5-1.5B-Instruct at eight llama.cpp GGUF precision levels (F16 t...