onnx-community/LFM2-8B-A1B-ONNX

Try LFM • Documentation • LEAP

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

1. ONNXRuntime

from transformers import AutoConfig, AutoTokenizer
import onnxruntime
import numpy as np
from huggingface_hub import snapshot_download

# 1. Load config, processor, and model
model_id = "onnx-community/LFM2-8B-A1B-ONNX"
config = AutoConfig.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)

local_dir = "LFM2-8B-A1B-ONNX"
model_path = snapshot_download(model_id, local_dir=local_dir, allow_patterns=["onnx/model_q4.onnx", "onnx/model_q4.onnx_data*"])  # Download model graph and weights
session = onnxruntime.InferenceSession(model_path)

## Set config values
num_key_value_heads = config.num_key_value_heads
head_dim = config.hidden_size // config.num_attention_heads
num_hidden_layers = config.num_hidden_layers
eos_token_id = config.eos_token_id
hidden_size = config.hidden_size
conv_L_cache = config.conv_L_cache
layer_types = config.layer_types

# 2. Prepare inputs
prompt = "What is C. elegans?"
messages = [{"role": "user", "content": prompt}]
inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="np")
input_ids = inputs['input_ids']
attention_mask = inputs['attention_mask']
batch_size = input_ids.shape[0]
past_cache_values = {}
for i in range(num_hidden_layers):
  if layer_types[i] == 'full_attention':
    for kv in ('key', 'value'):
      past_cache_values[f'past_key_values.{i}.{kv}'] = np.zeros([batch_size, num_key_value_heads, 0, head_dim], dtype=np.float32)
  elif layer_types[i] == 'conv':
    past_cache_values[f'past_conv.{i}'] = np.zeros([batch_size, hidden_size, conv_L_cache], dtype=np.float32)
  else:
    raise ValueError(f"Unsupported layer type: {layer_types[i]}")

# 3. Generation loop
max_new_tokens = 1024
generated_tokens = np.array([[]], dtype=np.int64)
for i in range(max_new_tokens):
  logits, *present_cache_values = session.run(None, dict(
      input_ids=input_ids,
      attention_mask=attention_mask,
      **past_cache_values,
  ))

  ## Update values for next generation loop
  input_ids = logits[:, -1].argmax(-1, keepdims=True)
  attention_mask = np.concatenate([attention_mask, np.ones_like(input_ids, dtype=np.int64)], axis=-1)
  for j, key in enumerate(past_cache_values):
    past_cache_values[key] = present_cache_values[j]
  generated_tokens = np.concatenate([generated_tokens, input_ids], axis=-1)
  if (input_ids == eos_token_id).all():
    break

  ## (Optional) Streaming
  print(tokenizer.decode(input_ids[0]), end='', flush=True)
print()

# 4. Output result
print(tokenizer.batch_decode(generated_tokens, skip_special_tokens=True)[0])

🔧 How to fine-tune LFM2

We recommend fine-tuning LFM2 models on your use cases to maximize performance.

Notebook	Description	Link
SFT (TRL)	Supervised Fine-Tuning (SFT) notebook with a LoRA adapter using TRL.
DPO (TRL)	Preference alignment with Direct Preference Optimization (DPO) using TRL.

📈 Performance

1. Automated benchmarks

[![Benchmarks](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/6xXgpyyK5htUZlHdpZab-.png)](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/6xXgpyyK5htUZlHdpZab-.png)

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.

[![Decode Throughput - S24 Ultra](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/AdR74EuIH_qJre89qaq62.png)](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/AdR74EuIH_qJre89qaq62.png)




[![Decode Throughput - HX370](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/YzmQXbmcv5WuVJ1tI2Jbh.png)](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/YzmQXbmcv5WuVJ1tI2Jbh.png)

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.

[![Prefill Throughput vs Sequence Length](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/NC4XN11RJB-Ifh758os3e.png)](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/NC4XN11RJB-Ifh758os3e.png)



[![Decode Throughput vs Sequence Length](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/6oAenHRxKIyvJOgdCetlF.png)](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/6oAenHRxKIyvJOgdCetlF.png)

📬 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}
}