Instructions to use LiquidAI/LFM2-2.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LiquidAI/LFM2-2.6B with Transformers:

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

pipe = pipeline("text-generation", model="LiquidAI/LFM2-2.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2-2.6B")
model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2-2.6B")
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/LFM2-2.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LiquidAI/LFM2-2.6B"
# 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/LFM2-2.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LiquidAI/LFM2-2.6B

SGLang

How to use LiquidAI/LFM2-2.6B 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/LFM2-2.6B" \
    --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/LFM2-2.6B",
		"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/LFM2-2.6B" \
        --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/LFM2-2.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LiquidAI/LFM2-2.6B with Docker Model Runner:
```
docker model run hf.co/LiquidAI/LFM2-2.6B
```

mlabonne commited on Sep 23, 2025

Commit

005bf33

verified ·

1 Parent(s): 0c0603c

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -208,7 +208,7 @@ You can directly run and test the model with this [Colab notebook](https://colab
 You need to install [`vLLM`](https://github.com/vllm-project/vllm) v0.10.2 or a more recent version as follows:
 ```bash
-uv pip install vllm --extra-index-url https://wheels.vllm.ai/0.10.2/ --torch-backend=auto
 ```
 Here is an example of how to use it for inference:
@@ -223,7 +223,7 @@ prompts = [
 ]
 sampling_params = SamplingParams(temperature=0.3, min_p=0.15, repetition_penalty=1.05)
-llm = LLM(model="LiquidAI/LFM2-350M")
 outputs = llm.generate(prompts, sampling_params)
@@ -257,10 +257,10 @@ LFM2 outperforms similar-sized models across different evaluation categories. We
 | Model                  | MMLU  | GPQA  | IFEval | IFBench | GSM8K | MGSM  | MMMLU |
 | ---------------------- | ----- | ----- | ------ | ------- | ----- | ----- | ----- |
 | LFM2-2.6B              | 64.42 | 26.57 | 79.56  | 22.19   | 82.41 | 74.32 | 55.39 |
-| Qwen3-4B-Instruct-2507 | 72.25 | 34.85 | 85.62  | 30.28   | 68.46 | 81.76 | 60.67 |
 | SmolLM3-3B             | 59.84 | 26.31 | 72.44  | 17.93   | 81.12 | 68.72 | 50.02 |
 | gemma-3-4b-it          | 58.35 | 29.51 | 76.85  | 23.53   | 89.92 | 87.28 | 50.14 |
-| Llama-3.2-3B-Instruct  | 60.35 | 30.6  | 71.43  | 20.78   | 75.21 | 61.68 | 47.92 |
 ## 📬 Contact

 You need to install [`vLLM`](https://github.com/vllm-project/vllm) v0.10.2 or a more recent version as follows:
 ```bash
+uv pip install vllm==0.10.2 --extra-index-url https://wheels.vllm.ai/0.10.2/ --torch-backend=auto
 ```
 Here is an example of how to use it for inference:
 ]
 sampling_params = SamplingParams(temperature=0.3, min_p=0.15, repetition_penalty=1.05)
+llm = LLM(model="LiquidAI/LFM2-2.6B")
 outputs = llm.generate(prompts, sampling_params)
 | Model                  | MMLU  | GPQA  | IFEval | IFBench | GSM8K | MGSM  | MMMLU |
 | ---------------------- | ----- | ----- | ------ | ------- | ----- | ----- | ----- |
 | LFM2-2.6B              | 64.42 | 26.57 | 79.56  | 22.19   | 82.41 | 74.32 | 55.39 |
+| Llama-3.2-3B-Instruct  | 60.35 | 30.6  | 71.43  | 20.78   | 75.21 | 61.68 | 47.92 |
 | SmolLM3-3B             | 59.84 | 26.31 | 72.44  | 17.93   | 81.12 | 68.72 | 50.02 |
 | gemma-3-4b-it          | 58.35 | 29.51 | 76.85  | 23.53   | 89.92 | 87.28 | 50.14 |
+| Qwen3-4B-Instruct-2507 | 72.25 | 34.85 | 85.62  | 30.28   | 68.46 | 81.76 | 60.67 |
 ## 📬 Contact