LFM2-VL support with GGUF and llama.cpp 🥳

You can now run these tiny, hyper-efficient VLMs on your watch!

We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on @huggingface pic.twitter.com/DfK3p1MA08

— Maxime Labonne @ ICLR (@maximelabonne) 18 août 2025

LFM2-VL support with GGUF and llama.cpp You can now run these tiny, hyper-efficient VLMs on your watch! We released quantized checkpoints for LFM2-VL-450M and LFM2-VL-1.6B on @huggingface

→ View original post on X — @maximelabonne