---
license: other
base_model: LiquidAI/LFM2.5-2.6B
quantized_by: ljupco
tags:
- llama.cpp
- gguf
- lfm2.5
---

# LFM2.5-2.6B — GGUF (Q4_K_M)

A GGUF conversion of LiquidAI's LFM2.5-2.6B for llama.cpp / vllm.cpp, quantized with
Q4_K (4-bit). This is one of the four models benchmarked in the three-engine report:

* [llama.cpp / ik-llama.cpp / vllm.cpp report](https://huggingface.co/ljupco/LFM2.5-2.6B-GGUF)

## Usage

```
llama-cli -m LFM2.5-2.6B-Q4_K_M.gguf -p "The capital of France is" -n 64
```

## Credits and Acknowledgements

This is a quantization of **LFM2.5-2.6B** by **Liquid AI**. We are deeply grateful to
Liquid AI for the LFM2.5 family, its gated-delta / shortconv architecture, and for
publishing the weights openly. This work builds directly on theirs, and we thank them
profusely. See the report above for the full acknowledgement.