tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2.5-350M") model = AutoModelForMultimodalLM.from_pretrained("LiquidAI/LFM2.5-350M") 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/LFM2.5-350M with vLLM:

Install from pip and serve model

Install vLLM from pip:

pip install vllm

Start the vLLM server:

vllm serve "LiquidAI/LFM2.5-350M"

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/LFM2.5-350M", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'

Use Docker

docker model run hf.co/LiquidAI/LFM2.5-350M

SGLang

How to use LiquidAI/LFM2.5-350M 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/LFM2.5-350M" \ --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/LFM2.5-350M", "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=" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "LiquidAI/LFM2.5-350M" \ --host 0.0.0.0 \ --port 30000

Call the server using curl (OpenAI-compatible API):

Docker Model Runner

How to use LiquidAI/LFM2.5-350M with Docker Model Runner:

docker model run hf.co/LiquidAI/LFM2.5-350M

Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.
LFM2.5-350M
🗒️ Model Details
Chat Template
Tool Use
🏃 Inference
🔧 Fine-Tuning
📊 Performance
Benchmarks
CPU Inference
GPU Inference
📬 Contact
Citation

Liquid AI

Try LFM • Docs • LEAP • Discord

LFM2.5-350M

LFM2.5 is a new family of hybrid models designed for on-device deployment. It builds on the LFM2 architecture with extended pre-training and reinforcement learning.

Best-in-class performance : A 350M model rivaling much larger models, bringing high-quality AI to your pocket.
Fast edge inference : 313 tok/s decode on AMD CPU, 188 tok/s on Snapdragon Gen4. Runs under 1GB of memory with day-one support for llama.cpp, MLX, and vLLM.
Scaled training : Extended pre-training from 10T to 28T tokens and large-scale multi-stage reinforcement learning.

Find more information about LFM2.5-350M in our blog post.

💻 Demo : https://huggingface.co/spaces/webml-community/lfm2.5-webgpu-summarizer

🗒️ Model Details

Model | Parameters | Description

LFM2.5-350M-Base | 350M | Pre-trained base model for fine-tuning LFM2.5-350M | 350M | General-purpose instruction-tuned model

LFM2.5-350M is a general-purpose text-only model with the following features:

Number of parameters : 350M
Number of layers : 16 (10 double-gated LIV convolution blocks + 6 GQA blocks)
Training budget : 28T tokens
Context length : 32,768 tokens
Vocabulary size : 65,536
Knowledge cutoff : Mid-2024
Languages : English, Arabic, Chinese, French, German, Japanese, Korean, Portuguese, Spanish
Generation parameters :
temperature: 0.1
top_k: 50
repetition_penalty: 1.05

Model | Description

LFM2.5-350M | Original model checkpoint in native format. Best for fine-tuning or inference with Transformers and vLLM. LFM2.5-350M-GGUF | Quantized format for llama.cpp and compatible tools. Optimized for CPU inference and local deployment with reduced memory usage. LFM2.5-350M-ONNX | ONNX Runtime format for cross-platform deployment. Enables hardware-accelerated inference across diverse environments (cloud, edge, mobile). LFM2.5-350M-MLX | MLX format for Apple Silicon. Optimized for fast inference on Mac devices using the MLX framework. LFM2.5-350M-OpenVINO | OpenVINO format for Intel hardware acceleration. Optimized for efficient inference on Intel CPUs, GPUs, and NPUs.

We recommend using it for data extraction, structured outputs, and tool use. It is not recommended for knowledge-intensive tasks and programming.

Chat Template

LFM2.5 uses a ChatML-like format. See the Chat Template documentation for details. Example:

You can use tokenizer.apply_chat_template() to format your messages automatically.

Tool Use

LFM2.5 supports function calling as follows:

Function definition : We recommend providing the list of tools as a JSON object in the system prompt. You can also use the tokenizer.apply_chat_template() function with tools.
Function call : By default, LFM2.5 writes Pythonic function calls (a Python list between <|tool_call_start|> and <|tool_call_end|> special tokens), as the assistant answer. You can override this behavior by asking the model to output JSON function calls in the system prompt.
Function execution : The function call is executed, and the result is returned as a "tool" role.
Final answer : LFM2 interprets the outcome of the function call to address the original user prompt in plain text.

See the Tool Use documentation for the full guide. Example:

<|startoftext|><|im_start|>system List of tools: [{"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"]}}]<|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 [{"candidate_id": "12345", "status": "Interview Scheduled", "position": "Clinical Research Associate", "date": "2023-11-20"}]<|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|>

🏃 Inference

LFM2.5 is supported by many inference frameworks. See the Inference documentation for the full list.

Name | Description | Docs | Notebook

Here's a quick start example with Transformers:

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

model_id = "LiquidAI/LFM2.5-350M" model = AutoModelForCausalLM.from_pretrained( model_id, device_map="auto", dtype="bfloat16",

attn_implementation="flash_attention_2" <- uncomment on compatible GPU

) tokenizer = AutoTokenizer.from_pretrained(model_id) streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)

prompt = "What is C. elegans?"

input_ids = tokenizer.apply_chat_template( [{"role": "user", "content": prompt}], add_generation_prompt=True, return_tensors="pt", tokenize=True, )["input_ids"].to(model.device)

output = model.generate( input_ids, do_sample=True, temperature=0.1, top_k=50, repetition_penalty=1.05, max_new_tokens=512, streamer=streamer, )

🔧 Fine-Tuning

We recommend fine-tuning LFM2.5 for your specific use case to achieve the best results.

Name | Description | Docs | Notebook

📊 Performance

Benchmarks

LFM2.5-350M | 30.64 | 20.01 | 76.96 | 40.69 | 44.92 LFM2-350M | 27.58 | 19.29 | 64.96 | 18.20 | 32.92 Granite 4.0-H-350M | 22.32 | 13.14 | 61.27 | 17.22 | 28.70 Granite 4.0-350M | 25.91 | 12.84 | 53.48 | 15.98 | 24.21 Qwen3.5-0.8B (Instruct) | 27.41 | 37.42 | 59.94 | 22.87 | 41.68 Qwen3.5-0.8B (Thinking) | 19.29 | -* | 32.93 | 22.00 | 26.44 Gemma 3 1B IT | 23.89 | 14.04 | 63.49 | 20.33 | 44.25

LFM2.5-350M | 32.45 | 44.11 | 21.86 | 18.86 | 17.84 LFM2-350M | 11.67 | 22.95 | 12.29 | 10.82 | 5.56 Granite 4.0-H-350M | 12.44 | 43.07 | 13.28 | 13.74 | 6.14 Granite 4.0-350M | 0.84 | 39.58 | 13.73 | 2.92 | 6.14 Qwen3.5-0.8B (Instruct) | 13.83 | 35.08 | 18.70 | 12.57 | 6.14 Qwen3.5-0.8B (Thinking) | 0.39 | 39.64 | 25.39 | 14.33 | 7.02 Gemma 3 1B IT | 2.28 | 16.61 | 7.17 | 9.36 | 6.43

*Evaluation could not be completed due to doom looping.

CPU Inference

GPU Inference

📬 Contact

Got questions or want to connect? Join our Discord community
If you are interested in custom solutions with edge deployment, please contact our sales team.

Citation

@article{liquidAI2026350M, author = {Liquid AI}, title = {LFM2.5-350M: No Size Left Behind}, journal = {Liquid AI Blog}, year = {2026}, note = {www.liquid.ai/blog/lfm2-5-350m-no-size-left-behind}, }

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

Downloads last month 81,606

Safetensors

Model size

0.4B params

Tensor type

BF16

Chat template

Files info

Inference Providers NEW

Text Generation

This model isn't deployed by any Inference Provider. 🙋 8 Ask for provider support