---
base_model:
- LiquidAI/LFM2-350M
---


# LFM2‑350M • Quantized Version (GGUF)

Quantized GGUF version of the `LiquidAI/LFM2-350M` model.

* ✅ Format: `GGUF`
* ✅ Use with: `liquid_llama.cpp`
* ✅ Supported precisions: `Q4_0`, `Q4_K`, etc.

## Download

```bash
wget https://huggingface.co/yasserrmd/LFM2-350M-gguf/resolve/main/lfm2-350m.Q4_K.gguf
```

*(Adjust filename for other quant formats like `Q4_0`, if available.)*


## Notes

* Only compatible with `liquid_llama.cpp` (not `llama.cpp`).
* Replace `Q4_K` with your chosen quant version.