Instructions to use unsloth/LFM2-1.2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use unsloth/LFM2-1.2B with Transformers:

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

pipe = pipeline("text-generation", model="unsloth/LFM2-1.2B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("unsloth/LFM2-1.2B")
model = AutoModelForCausalLM.from_pretrained("unsloth/LFM2-1.2B")
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 unsloth/LFM2-1.2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/LFM2-1.2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/LFM2-1.2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/unsloth/LFM2-1.2B

SGLang

How to use unsloth/LFM2-1.2B 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 "unsloth/LFM2-1.2B" \
    --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": "unsloth/LFM2-1.2B",
		"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 "unsloth/LFM2-1.2B" \
        --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": "unsloth/LFM2-1.2B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use unsloth/LFM2-1.2B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/LFM2-1.2B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/LFM2-1.2B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/LFM2-1.2B to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="unsloth/LFM2-1.2B",
    max_seq_length=2048,
)

Docker Model Runner
How to use unsloth/LFM2-1.2B with Docker Model Runner:
```
docker model run hf.co/unsloth/LFM2-1.2B
```

danielhanchen commited on Jul 14, 2025

Commit

69c2974

verified ·

1 Parent(s): 2352535

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +8 -4

README.md CHANGED Viewed

@@ -21,10 +21,6 @@ tags:
 - lfm2
 - edge
 ---
-> [!NOTE]
->  Includes our **chat template fixes**! <br> For `llama.cpp`, use `--jinja`
->
 <div>
 <p style="margin-top: 0;margin-bottom: 0;">
     <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
@@ -161,6 +157,10 @@ The candidate with ID 12345 is currently in the "Interview Scheduled" stage for
 ## 🏃 How to run LFM2
 To run LFM2, you need to install Hugging Face [`transformers`](https://github.com/huggingface/transformers) from source (v4.54.0.dev0).
 You can update or install it with the following command: `pip install "transformers @ git+https://github.com/huggingface/transformers.git@main"`.
@@ -209,6 +209,10 @@ print(tokenizer.decode(output[0], skip_special_tokens=False))
 You can directly run and test the model with this [Colab notebook](https://colab.research.google.com/drive/1_q3jQ6LtyiuPzFZv7Vw8xSfPU5FwkKZY?usp=sharing).
 ## 🔧 How to fine-tune LFM2
 We recommend fine-tuning LFM2 models on your use cases to maximize performance.

 - lfm2
 - edge
 ---
 <div>
 <p style="margin-top: 0;margin-bottom: 0;">
     <em><a href="https://docs.unsloth.ai/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0</a> achieves superior accuracy & outperforms other leading quants.</em>
 ## 🏃 How to run LFM2
+You can run LFM2 with transformers and llama.cpp. vLLM support is coming.
+### 1. Transformers
 To run LFM2, you need to install Hugging Face [`transformers`](https://github.com/huggingface/transformers) from source (v4.54.0.dev0).
 You can update or install it with the following command: `pip install "transformers @ git+https://github.com/huggingface/transformers.git@main"`.
 You can directly run and test the model with this [Colab notebook](https://colab.research.google.com/drive/1_q3jQ6LtyiuPzFZv7Vw8xSfPU5FwkKZY?usp=sharing).
+### 2. Llama.cpp
+You can run LFM2 with llama.cpp using its [GGUF checkpoint](https://huggingface.co/LiquidAI/LFM2-1.2B-GGUF). Find more information in the model card.
 ## 🔧 How to fine-tune LFM2
 We recommend fine-tuning LFM2 models on your use cases to maximize performance.