Instructions to use blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated")
model = AutoModelForMultimodalLM.from_pretrained("blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated

SGLang

How to use blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated with Docker Model Runner:
```
docker model run hf.co/blockblockblock/LFM2.5-8B-A1B-uncensored-abliterated
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

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

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

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.

Model Details

Model size: 8B params
Tensor type: F32 / BF16
Architecture: Hybrid (18 conv + 6 attention layers)
Paper: LFM2 Technical Report

License

This model uses the LFM 1.0 License.

Citation

@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}
}