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

Libraries

How to use LiquidAI/LFM2-8B-A1B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2-8B-A1B")
model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2-8B-A1B")
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

vLLM

How to use LiquidAI/LFM2-8B-A1B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LiquidAI/LFM2-8B-A1B

SGLang

How to use LiquidAI/LFM2-8B-A1B 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 "LiquidAI/LFM2-8B-A1B" \
    --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": "LiquidAI/LFM2-8B-A1B",
		"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 "LiquidAI/LFM2-8B-A1B" \
        --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": "LiquidAI/LFM2-8B-A1B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LiquidAI/LFM2-8B-A1B with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2-8B-A1B
```

How is the 2.6b model better than this one in literally every use case I have???

by cinnybun02 - opened Dec 21, 2025

Discussion

cinnybun02

Dec 21, 2025

The benchmarks show this moe variant is better and it should be but that's not the case. Hell the Q4_km version of 2.6b performs better somehow.

mlabonne

Liquid AI org Dec 21, 2025

Yes, this model is stronger overall (especially in code), but maybe not for your particular use cases. Could you tell us more about them?

OMS23

Dec 22, 2025

•

edited Dec 22, 2025

@mlabonne

There is a theory that said MoE model aren't that good in small scale, basically at small parameters count it will be worse in some way than the dense counter part.

But it still gonna be better at big scale.

I could be wrong but it's seems like that

mlabonne

Liquid AI org Dec 23, 2025

Do you have a reference for this theory? I believe the trade-offs between dense and MoE models are well understood overall. In this specific case, LFM2-2.6B is a very deep model, unlike this MoE. It means that reasoning-heavy tasks might work better with the 2.6B, but that is very use-case-dependent. Overall, LFM2-8B-A1B is a stronger (and faster) model.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment