LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF/README.md

---
base_model: ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth
tags:
- gguf
- llama.cpp
- unsloth
- lfm2
- reasoning
- quantized
license: apache-2.0
language:
- en
datasets:
- ermiaazarkhalili/Claude-Opus-4.7-Reasoning
pipeline_tag: text-generation
---

# LFM2.5-1.2B-SFT-Unsloth — GGUF quantized

GGUF quantizations of [`ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth`](https://huggingface.co/ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth),
produced via [Unsloth](https://github.com/unslothai/unsloth) + llama.cpp's conversion scripts.

| Field | Value |
|---|---|
| **Source checkpoint** | [`ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth`](https://huggingface.co/ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth) |
| **Base model** | [`LiquidAI/LFM2.5-1.2B-Instruct`](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct) |
| **Dataset** | [`ermiaazarkhalili/Claude-Opus-4.7-Reasoning`](https://huggingface.co/datasets/ermiaazarkhalili/Claude-Opus-4.7-Reasoning) |
| **Training** | N=1 full epoch (N=1 epoch steps, effective batch=8) |
| **Conversion** | Unsloth `save_pretrained_gguf` → llama.cpp GGUF |
| **Quantization tool** | llama.cpp `llama-quantize` |

## Available quantizations

| File | Size | Notes |
|---|---|---|
| `LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth.Q2_K.gguf` | smallest | 2-bit; extreme compression, quality loss |
| `LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth.Q3_K_M.gguf` | small | 3-bit; modest quality trade-off |
| `LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth.Q4_K_M.gguf` | recommended | 4-bit; best size/quality balance |
| `LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth.Q5_K_M.gguf` | balanced | 5-bit; near-full quality |
| `LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth.Q6_K.gguf` | high quality | 6-bit; minimal degradation |
| `LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth.Q8_0.gguf` | largest | 8-bit; closest to bf16 source |

**Recommended default:** `Q4_K_M` (4-bit, K-quant medium). For memory-constrained deployment, try `Q2_K` or `Q3_K_M`. For maximum fidelity, use `Q8_0`.

## Usage

### llama.cpp

```bash
# Text-only
llama-cli -hf ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF --jinja -p "Explain step-by-step: if a train travels 60 mph for 2.5 hours, how far does it go?" -n 256

# Interactive chat
llama-cli -hf ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF --jinja -cnv
```

### Ollama

```bash
ollama run hf.co/ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF:Q4_K_M
```

### llama-cpp-python

```python
from llama_cpp import Llama
llm = Llama.from_pretrained(
    repo_id="ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF",
    filename="*Q4_K_M.gguf",
    n_ctx=2048,
)
out = llm.create_chat_completion(
    messages=[{"role": "user", "content": "Explain step-by-step: if a train travels 60 mph for 2.5 hours, how far does it go?"}],
    max_tokens=256,
)
print(out["choices"][0]["message"]["content"])
```

## Intended use

For research and non-commercial experimentation only. Outputs should be independently verified before any downstream use.

## Limitations

- GGUF quantizations have unavoidable quality loss relative to the source bfloat16 checkpoint. Use `Q5_K_M` or `Q8_0` for best fidelity.
- Inherits all limitations of the source merged checkpoint ([`ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth`](https://huggingface.co/ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth)).
- Distilled reasoning traces reflect patterns from Claude Opus 4.7 and may not generalize to domains outside the distillation corpus.

## Citation

```bibtex
@misc{ lfm25_12b_sft_claude_opus_2026_gguf ,
  author = {Ermia Azarkhalili},
  title = { LFM2.5-1.2B-SFT-Unsloth — GGUF quantized },
  year = {2026},
  publisher = {Hugging Face},
  howpublished = {\url{https://huggingface.co/ermiaazarkhalili/LFM2.5-1.2B-SFT-Claude-Opus-Reasoning-Unsloth-GGUF}}
}
```

---

This lfm2 model was trained 2× faster with [Unsloth](https://github.com/unslothai/unsloth) and Hugging Face's TRL library.

[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)