I suggest re-pulling the model since I have updated the parameters, use ollama pull Maternion/lfm2:8b to re-pull.

In case the model crashes, make sure to use the latest version of Ollama with OLLAMA_NEW_ENGINE=1 set in environment variables, for more info check here.

LFM2-8B-A1B

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 our first MoE based on LFM2, with 8.3B total parameters and 1.5B active parameters.

• LFM2-8B-A1B is the best on-device MoE in terms of both quality (comparable to 3-4B dense models) and speed (faster than Qwen3-1.7B).
• Code and knowledge capabilities are significantly improved compared to LFM2-2.6B.
• Quantized variants fit comfortably on high-end phones, tablets, and laptops.

Find more information about LFM2-8B-A1B 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.

Supported languages: English, Arabic, Chinese, French, German, Japanese, Korean, and Spanish.

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: 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 2. Function call: LFM2 writes Pythonic function calls (a Python list between <|tool_call_start|> and <|tool_call_end|> special tokens), as the assistant answer. 3. 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. 4. 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: 18 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: * 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

Ollama

To run LFM2-8B-A1B you need to download Ollama. Then you need to run:

ollama run Maternion/lfm2:8b

📈 Performance

1. Automated benchmarks

Compared to similar-sized models, LFM2-8B-A1B displays strong performance in instruction following and math while also running significantly faster.

2. Inference

LFM2-8B-A1B is significantly faster than models with a similar number of active parameters, like Qwen3-1.7B.

The following plots showcase the performance of different models under int4 quantization with int8 dynamic activations on the AMD Ryzen AI 9 HX 370 CPU, using 16 threads. The results are obtained using our internal XNNPACK-based inference stack, and a custom CPU MoE kernel.

📬 Contact

If you are interested in custom solutions with edge deployment, please contact our sales team.

Citation

@article{liquidai2025lfm2,
 title={LFM2 Technical Report},
 author={Liquid AI},
 journal={arXiv preprint arXiv:2511.23404},
 year={2025}
}