Paper summary
Paper summary: SmolVLM: Redefining small and efficient multimodal models
SmolVLM is a family of compact vision-language models designed for on-device inference; the 256M model uses under 1GB of GPU memory and is reported to beat the 300× larger Idefics-80B.
- Small VLMs shouldn't just copy big ones: SmolVLM rethinks tokenisation and architecture for low memory.
- The 256M model runs in under 1GB of GPU memory.