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
| Model | Parameters | Description |
|---|---|---|
| LFM2.5-24B-A2B-Base | 24B (2B active) | Pre-trained base model for fine-tuning |
| LFM2.5-24B-A2B | 24B (2B active) | Post-trained for agentic workloads |
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:
| Model | Description |
|---|---|
| LFM2.5-24B-A2B | Original post-trained model checkpoint in native format. Best for fine-tuning or inference with Transformers, vLLM, and SGLang. |
| LFM2.5-24B-A2B-GGUF | Quantized format for llama.cpp and compatible tools. Optimized for CPU inference and local deployment with reduced memory usage. |
| LFM2.5-24B-A2B-ONNX | ONNX Runtime format for cross-platform deployment. Enables hardware-accelerated inference across diverse environments (cloud, edge, mobile). |
| LFM2.5-24B-A2B-MLX | MLX format for Apple Silicon. Optimized for fast inference on Mac devices using the MLX framework. |
🏃 Inference
LFM2.5 is supported by many inference frameworks. See the Inference documentation for the full list.
| Name | Description | Docs | Notebook |
|---|---|---|---|
| Transformers | Simple inference with direct access to model internals. | Link | |
| vLLM | High-throughput production deployments with GPU. | Link | |
| llama.cpp | Cross-platform inference with CPU offloading. | Link | |
| MLX | Apple's machine learning framework optimized for Apple Silicon. | Link | — |
| LM Studio | Desktop application for running LLMs locally. | Link | — |
| SGLang | High-throughput production deployments with GPU. | Link | - |
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.
| Name | Description | Docs | Notebook |
|---|---|---|---|
| CPT (Unsloth) | Continued Pre-Training using Unsloth for text completion. | Link | |
| CPT (Unsloth) | Continued Pre-Training using Unsloth for translation. | Link | |
| SFT (Unsloth) | Supervised Fine-Tuning with LoRA using Unsloth. | Link | |
| SFT (TRL) | Supervised Fine-Tuning with LoRA using TRL. | Link | |
| DPO (TRL) | Direct Preference Optimization with LoRA using TRL. | Link | |
| GRPO (Unsloth) | GRPO with LoRA using Unsloth. | Link | |
| GRPO (TRL) | GRPO with LoRA using TRL. | Link |
📬 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}
}