Instructions to use LiquidAI/LFM2-350M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM2-350M with Transformers:

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

pipe = pipeline("text-generation", model="LiquidAI/LFM2-350M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2-350M")
model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2-350M", device_map="auto")
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 LiquidAI/LFM2-350M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM2-350M"
# 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/LFM2-350M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM2-350M

SGLang

How to use LiquidAI/LFM2-350M 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/LFM2-350M" \
    --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/LFM2-350M",
		"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/LFM2-350M" \
        --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/LFM2-350M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LiquidAI/LFM2-350M with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2-350M
```

mlabonne commited on Aug 12, 2025

Commit

6a8f6ca

verified ·

1 Parent(s): 0fa3ebc

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -10

README.md CHANGED Viewed

@@ -74,15 +74,15 @@ Due to their small size, **we recommend fine-tuning LFM2 models on narrow use ca
 They are particularly suited for agentic tasks, data extraction, RAG, creative writing, and multi-turn conversations.
 However, we do not recommend using them for tasks that are knowledge-intensive or require programming skills.
-| Property            | Value                         |
-| ------------------- | ----------------------------- |
-| **Parameters**      | 354,483,968                   |
-| **Layers**          | 16 (10 conv + 6 attn)         |
-| **Context length**  | 32,768 tokens                 |
-| **Vocabulary size** | 65,536                        |
-| **Precision**       | bfloat16                      |
-| **Training budget** | 10 trillion tokens            |
-| **License**         | LFM Open License v1.0         |
 **Supported languages**: English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish.
@@ -102,7 +102,7 @@ What is C. elegans?<|im_end|>
 It's a tiny nematode that lives in temperate soil environments.<|im_end|>
 ```
-You can apply it using the dedicated [`.apply_chat_template()`](https://huggingface.co/docs/transformers/en/chat_templating#applychattemplate) function from Hugging Face transformers.
 **Tool use**: It consists of four main steps:
 1. **Function definition**: LFM2 takes JSON function definitions as input (JSON objects between `<|tool_list_start|>` and `<|tool_list_end|>` special tokens), usually in the system prompt

 They are particularly suited for agentic tasks, data extraction, RAG, creative writing, and multi-turn conversations.
 However, we do not recommend using them for tasks that are knowledge-intensive or require programming skills.
+| Property            | [**LFM2-350M**](https://huggingface.co/LiquidAI/LFM2-350M)                 | [**LFM2-700M**](https://huggingface.co/LiquidAI/LFM2-700M)                 | [**LFM2-1.2B**](https://huggingface.co/LiquidAI/LFM2-1.2B)                 |
+| ------------------- | ----------------------------- | ----------------------------- | ----------------------------- |
+| **Parameters**      | 354,483,968                   | 742,489,344                   | 1,170,340,608                 |
+| **Layers**          | 16 (10 conv + 6 attn)         | 16 (10 conv + 6 attn)         | 16 (10 conv + 6 attn)         |
+| **Context length**  | 32,768 tokens                 | 32,768 tokens                 | 32,768 tokens                 |
+| **Vocabulary size** | 65,536                        | 65,536                        | 65,536                        |
+| **Precision**       | bfloat16                      | bfloat16                      | bfloat16                      |
+| **Training budget** | 10 trillion tokens            | 10 trillion tokens            | 10 trillion tokens            |
+| **License**         | LFM Open License v1.0         | LFM Open License v1.0         | LFM Open License v1.0         |
 **Supported languages**: English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish.
 It's a tiny nematode that lives in temperate soil environments.<|im_end|>
 ```
+You can automatically apply it using the dedicated [`.apply_chat_template()`](https://huggingface.co/docs/transformers/en/chat_templating#applychattemplate) function from Hugging Face transformers.
 **Tool use**: It consists of four main steps:
 1. **Function definition**: LFM2 takes JSON function definitions as input (JSON objects between `<|tool_list_start|>` and `<|tool_list_end|>` special tokens), usually in the system prompt