LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.
We're releasing the weights of four post-trained checkpoints with 350M, 700M, 1.2B, and 2.6 parameters. They provide the following key features to create AI-powered edge applications:
Fast training & inference – LFM2 achieves 3x faster training compared to its previous generation. It also benefits from 2x faster decode and prefill speed on CPU compared to Qwen3.
Best performance – LFM2 outperforms similarly-sized models across multiple benchmark categories, including knowledge, mathematics, instruction following, and multilingual capabilities.
New architecture – LFM2 is a new hybrid Liquid model with multiplicative gates and short convolutions.
Flexible deployment – LFM2 runs efficiently on CPU, GPU, and NPU hardware for flexible deployment on smartphones, laptops, or vehicles.
Find more information about LFM2 in our blog post.
📄 Model details
Due to their small size, we recommend fine-tuning LFM2 models on narrow use cases to maximize performance.
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.
Generation parameters: We recommend the following parameters:
temperature=0.3
min_p=0.15
repetition_penalty=1.05
Chat template: LFM2 uses a ChatML-like chat template as follows:
<|startoftext|><|im_start|>system
You are a helpful assistant trained by Liquid AI.<|im_end|>
<|im_start|>user
What is C. elegans?<|im_end|>
<|im_start|>assistant
It's a tiny nematode that lives in temperate soil environments.<|im_end|>
You can automatically apply it using the dedicated .apply_chat_template() function from Hugging Face transformers.
Tool use: It consists of four main steps:
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
Function call: LFM2 writes Pythonic function calls (a Python list between <|tool_call_start|> and <|tool_call_end|> special tokens), as the assistant answer.
Function execution: The function call is executed and the result is returned (string between <|tool_response_start|> and <|tool_response_end|> special tokens), as a "tool" role.
Final answer: LFM2 interprets the outcome of the function call to address the original user prompt in plain text.
Here is a simple example of a conversation using tool use:
<|startoftext|><|im_start|>system
List of tools: <|tool_list_start|>[{"name": "get_candidate_status", "description": "Retrieves the current status of a candidate in the recruitment process", "parameters": {"type": "object", "properties": {"candidate_id": {"type": "string", "description": "Unique identifier for the candidate"}}, "required": ["candidate_id"]}}]<|tool_list_end|><|im_end|>
<|im_start|>user
What is the current status of candidate ID 12345?<|im_end|>
<|im_start|>assistant
<|tool_call_start|>[get_candidate_status(candidate_id="12345")]<|tool_call_end|>Checking the current status of candidate ID 12345.<|im_end|>
<|im_start|>tool
<|tool_response_start|>[{"candidate_id": "12345", "status": "Interview Scheduled", "position": "Clinical Research Associate", "date": "2023-11-20"}]<|tool_response_end|><|im_end|>
<|im_start|>assistant
The candidate with ID 12345 is currently in the "Interview Scheduled" stage for the position of Clinical Research Associate, with an interview date set for 2023-11-20.<|im_end|>
You can directly pass tools as JSON schema or Python functions with .apply_chat_template() as shown in this page to automatically format the system prompt.
Architecture: Hybrid model with multiplicative gates and short convolutions: 10 double-gated short-range LIV convolution blocks and 6 grouped query attention (GQA) blocks.
Pre-training mixture: Approximately 75% English, 20% multilingual, and 5% code data sourced from the web and licensed materials.
Training approach:
Knowledge distillation using LFM1-7B as teacher model
Very large-scale SFT on 50% downstream tasks, 50% general domains
Custom DPO with length normalization and semi-online datasets
Iterative model merging
🏃 How to run LFM2
1. Transformers
To run LFM2, you need to install Hugging Face transformers v4.55 or a more recent version as follows:
pip install -U transformers
Here is an example of how to generate an answer with transformers in Python:
python
1from transformers import AutoModelForCausalLM, AutoTokenizer
23# Load model and tokenizer4model_id ="LiquidAI/LFM2-350M"5model = AutoModelForCausalLM.from_pretrained(6 model_id,7 device_map="auto",8 torch_dtype="bfloat16",9# attn_implementation="flash_attention_2" <- uncomment on compatible GPU10)11tokenizer = AutoTokenizer.from_pretrained(model_id)1213# Generate answer14prompt ="What is C. elegans?"15input_ids = tokenizer.apply_chat_template(16[{"role":"user","content": prompt}],17 add_generation_prompt=True,18 return_tensors="pt",19 tokenize=True,20).to(model.device)2122output = model.generate(23 input_ids,24 do_sample=True,25 temperature=0.3,26 min_p=0.15,27 repetition_penalty=1.05,28 max_new_tokens=512,29)3031print(tokenizer.decode(output[0], skip_special_tokens=False))3233# <|startoftext|><|im_start|>user34# What is C. elegans?<|im_end|>35# <|im_start|>assistant36# C. elegans, also known as Caenorhabditis elegans, is a small, free-living37# nematode worm (roundworm) that belongs to the phylum Nematoda.
You can directly run and test the model with this Colab notebook.
2. vLLM
You need to install vLLM v0.10.2 or a more recent version as follows:
