LFM2-24B-A2B-ONNX

<|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

<|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|>

npm i @huggingface/transformers

import { pipeline, TextStreamer } from "@huggingface/transformers";

// Create a text generation pipeline
const generator = await pipeline(
  "text-generation",
  "onnx-community/LFM2-24B-A2B-ONNX",
  { dtype: "q4f16", device: "webgpu" },
);

// Define the list of messages
const messages = [
  { role: "user", content: "What's the capital of France?" },
];

// Generate a response
const output = await generator(messages, {
  max_new_tokens: 512,
  do_sample: false,
  streamer: new TextStreamer(generator.tokenizer, {
    skip_prompt: true,
    skip_special_tokens: true,
  }),
});
console.log(output[0].generated_text.at(-1).content);

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/LFM2-24B-A2B-ONNX"
config = AutoConfig.from_pretrained(model_id)
tokenizer = AutoTokenizer.from_pretrained(model_id)
eos_token_id = config.eos_token_id

filename = "model_q4f16.onnx" # Options: "model_fp16.onnx", "model_q4f16.onnx"
model_path = snapshot_download(repo_id=model_id, allow_patterns=f"onnx/{filename}*") # Download the graph + weights
session = onnxruntime.InferenceSession(f"{model_path}/onnx/{filename}")

# 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]
num_logits_to_keep = np.array(1, dtype=np.int64)

past_cache_values = {}
for inp in session.get_inputs():
    name = inp.name
    shape = inp.shape
    dtype = np.float32 if inp.type == "tensor(float)" else np.float16
    if name.startswith("past_key_values"):
        # Attention KV cache: shape [batch_size, num_kv_heads, 0, head_dim]
        past_cache_values[name] = np.zeros([batch_size, shape[1], 0, shape[3]], dtype=dtype)
    elif name.startswith("past_conv"):
        # Conv cache: shape [batch_size, hidden_size, conv_L_cache]
        past_cache_values[name] = np.zeros([batch_size, shape[1], shape[2]], dtype=dtype)

# 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,
      num_logits_to_keep=num_logits_to_keep,
      **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 np.isin(input_ids, eos_token_id).any():
      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])

@article{liquidAI202624B,
  author = {Liquid AI},
  title = {LFM2.5-24B-A2B: Scaling Up the LFM2 Architecture},
  journal = {Liquid AI Blog},
  year = {2026},
  note = {www.liquid.ai/blog/},
}

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