---
base_model: LiquidAI/LFM2.5-8B-A1B
tags:
- transformers
- text-generation
- safetensors
- lfm2.5
- liquid
- conversational
- uncensored
- abliterated
---

# LFM2.5-8B-A1B-uncensored-abliterated

[![refusals](https://img.shields.io/badge/refusals-0%2F100-0f6e56?style=flat-square&labelColor=14120e)](#refusal-metrics)
[![base](https://img.shields.io/badge/base-LiquidAI%2FLFM2.5--8B--A1B-2a2620?style=flat-square&logo=huggingface&logoColor=white)](https://huggingface.co/LiquidAI/LFM2.5-8B-A1B)

#### AdvBench:
| | refusals (n=100) |
|---|---|
| original | 39/100 |
| this | 0/100 |

## Method

- Dual-path abliteration targeting LFM2.5 hybrid architecture (18 conv + 6 attention layers)
- 50 modules modified across all 24 layers (conv + attention paths)
- Refusal direction: harmful - harmless
- Per-module weights: attn=4.0, conv=3.0, ffn=2.5, in_proj=2.0
- 51 prompts for precise direction estimation

**License:** [LFM 1.0 License](https://www.liquid.ai/laion-license)

---

## Base Model Card (LiquidAI/LFM2.5-8B-A1B)

LFM2.5-8B-A1B

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.

- **On-device personal assistant**: Designed to power real-life applications, chaining tool calls, and following complex instructions on all devices.
- **Compressed performance**: Competitive with much larger dense and MoE models on instruction following and agentic tasks.
- **Unmatched throughput**: Fastest in its size class on both CPU and GPU inference, with day-one support for llama.cpp, MLX, vLLM, and SGLang.

Find more information about LFM2.5-8B-A1B in our [blog post](https://www.liquid.ai/blog/lfm2-5-8b-a1b).

### Model Details
- Model size: 8B params
- Tensor type: F32 / BF16
- Architecture: Hybrid (18 conv + 6 attention layers)
- Paper: [LFM2 Technical Report](https://arxiv.org/abs/2511.23404)

### License
This model uses the [LFM 1.0 License](https://www.liquid.ai/laion-license).

### Citation
```bibtex
@article{liquidAI20268BA1B,
  author  = {Liquid AI},
  title   = {LFM2.5-8B-A1B: Personal Assistant On Your Laptop},
  journal = {Liquid AI Blog},
  year    = {2026},
  note    = {www.liquid.ai/blog/lfm2-5-8b-a1b},
}

@article{liquidai2025lfm2,
  title   = {LFM2 Technical Report},
  author  = {Liquid AI},
  journal = {arXiv preprint arXiv:2511.23404},
  year    = {2025}
}
```