LFM2.5-24B-A2B-Base

Image: Liquid AI

Try LFM • Docs • Discord

LFM2.5-24B-A2B-Base#

LFM2.5 is a new family of hybrid models designed for on-device deployment. LFM2.5-24B-A2B is the largest model in the family: a 24B-parameter mixture of experts with only 2B active parameters. It builds on LFM2-24B-A2B with a 131K context window, a vocabulary doubled to 128K tokens, and pre-training scaled up from ~17T to ~33T tokens.

Find more information about LFM2.5-24B-A2B in our blog post.

🗒️ Model Details#

LFM2.5-24B-A2B-Base is the pre-trained text-only checkpoint, used to create all the LFM2.5-24B-A2B variants. It has the following features:

• Total parameters: 24.0B
• Active parameters: 2.45B
• Number of layers: 40 (30 double-gated short convolution blocks + 10 GQA)
• Experts: 64 per MoE block, top-4 routing
• Training budget: 36 trillion tokens
• Vocabulary size: 128,000
• Context length: 131,072 tokens
• Languages: English, Arabic, Chinese, French, German, Italian, Japanese, Korean, Portuguese, Spanish, Vietnamese, Thai, Indonesian, Hindi, Russian, Polish

Pre-training is followed by two mid-training phases: 2T tokens at 32K context on curated data weighted toward reasoning, math, code, instruction following, and multilingual text, then 300B tokens at 131K context weighted toward long-context data. Tool calls and multi-turn trajectories appear throughout both phases to prepare the model for agentic workloads.

This pre-trained checkpoint is only recommended for tasks that require heavy fine-tuning, like language-specific (e.g., Japanese) or domain-specific (e.g., medical) assistants, training on proprietary data, or experimenting with novel post-training approaches. Other checkpoints to consider for your use case:

🏃 Inference#

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

Quick start with Transformers (compatible with transformers>=5.0.0):

from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

model_id = "LiquidAI/LFM2.5-24B-A2B-Base"
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,
    max_new_tokens=512,
    streamer=streamer,
)

🔧 Fine-Tuning#

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

📬 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{liquidAI202624BA2B,
  author  = {Liquid AI},
  title   = {LFM2.5-24B-A2B: Built for Fast On-Device Agents},
  journal = {Liquid AI Blog},
  year    = {2026},
  note    = {www.liquid.ai/blog/lfm2-5-24b-a2b},
}

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