---
license: other
base_model: LiquidAI/LFM2.5-1.2B-JP-202606
tags:
- gguf
- llama.cpp
- lfm2
- japanese
- text-generation
language:
- ja
pipeline_tag: text-generation
---

# LFM-2.5-1.2B-Novel-JP-GGUF

GGUF quantized versions of a fine-tuned **LiquidAI LFM2.5-1.2B** (Japanese) model,
converted with [llama.cpp](https://github.com/ggml-org/llama.cpp) for local inference.

- **Base model:** `LiquidAI/LFM2.5-1.2B-JP-202606`
- **Architecture:** LFM2 (`Lfm2ForCausalLM`)
- **Format:** GGUF (llama.cpp compatible)

## Available quantizations

| File | Quant | Size | Notes |
|------|-------|------|-------|
| `LFM-2.5-1.2B-Novel-JP-F16.gguf`   | F16    | ~2.3 GB | Full precision, highest quality |
| `LFM-2.5-1.2B-Novel-JP-Q8_0.gguf`  | Q8_0   | ~1.2 GB | Near-lossless |
| `LFM-2.5-1.2B-Novel-JP-Q5_K_M.gguf`| Q5_K_M | ~843 MB | Balanced quality/size |
| `LFM-2.5-1.2B-Novel-JP-Q4_K_M.gguf`| Q4_K_M | ~731 MB | Smallest, recommended for most uses |

## Usage (llama.cpp)

```bash
huggingface-cli download TeamDelta/LFM-2.5-1.2B-Novel-JP-GGUF \
  LFM-2.5-1.2B-Novel-JP-Q4_K_M.gguf --local-dir .

llama-cli -m LFM-2.5-1.2B-Novel-JP-Q4_K_M.gguf -p "こんにちは" -cnv
```

## Usage (Ollama)

```bash
ollama run hf.co/TeamDelta/LFM-2.5-1.2B-Novel-JP-GGUF:Q4_K_M
```

---
*Converted and uploaded with llama.cpp inside the Unsloth Docker image.*