LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.

Find more details in the original model card: https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct

🏃 How to run LFM2.5

Example usage with llama.cpp:

llama-cli -hf LiquidAI/LFM2.5-1.2B-Instruct-GGUF --conversation \
    --temp 0.1 --top-k 50 --repeat-penalty 1.05

QAD Q4_0 GGUF

The Quantization-Aware Distillation (QAD) checkpoint is available as LFM2.5-1.2B-Instruct-QAD-Q4_0.gguf.

This is distinct from the post-training-quantized LFM2.5-1.2B-Instruct-Q4_0.gguf; both use the GGUF Q4_0 format.

Example usage with llama.cpp:

csharp

llama-cli -hf LiquidAI/LFM2.5-1.2B-Instruct-GGUF \
  --hf-file LFM2.5-1.2B-Instruct-QAD-Q4_0.gguf \
  -p "What is C. elegans?"

📬 Contact

Got questions or want to connect? Join our Discord community
If you are interested in custom solutions with edge deployment, please contact our sales team.