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 1.2B model rivaling much larger models, bringing high-quality AI to your pocket.
Fast edge inference: 239 tok/s decode on AMD CPU, 82 tok/s on mobile NPU. 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 in our blog post.
<|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
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.
<|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.
We compared LFM2.5-1.2B-Instruct with relevant sub-2B models on a diverse suite of benchmarks.
Model
GPQA
MMLU-Pro
IFEval
IFBench
Multi-IF
AIME25
BFCLv3
LFM2.5-1.2B-Instruct
38.89
44.35
86.23
47.33
60.98
14.00
49.12
Qwen3-1.7B
34.85
42.91
73.68
21.33
56.48
9.33
46.30
Granite 4.0-1B
24.24
33.53
79.61
21.00
43.65
3.33
52.43
Llama 3.2 1B Instruct
16.57
20.80
52.37
15.93
30.16
0.33
21.44
Gemma 3 1B IT
24.24
14.04
63.25
20.47
44.31
1.00
16.64
GPQA, MMLU-Pro, IFBench, and AIME25 follow ArtificialAnalysis's methodology. For IFEval and Multi-IF, we report the average score across strict and loose prompt and instruction accuracies. For BFCLv3, we report the final weighted average score with a custom Liquid handler to support our tool use template.
Inference speed
LFM2.5-1.2B-Instruct offers extremely fast inference speed on CPUs with a low memory profile compared to similar-sized models.
In addition, we are partnering with AMD, Qualcomm, and Nexa AI to bring the LFM2.5 family to NPUs. These optimized models are available through our partners, enabling highly efficient on-device inference.
These capabilities unlock new deployment scenarios across various devices, including vehicles, mobile devices, laptops, IoT devices, and embedded systems.
Contact
For enterprise solutions and edge deployment, contact sales@liquid.ai.
