LFM2.5-1.2B-Thinking

Reasoning-focused 1.2B parameter model with enhanced math and logical problem-solving

← Back to Text Models

LFM2.5-1.2B-Thinking is optimized for reasoning tasks, delivering strong performance on math, logic, and multi-step problem-solving. Built on the LFM2.5 architecture with specialized training for chain-of-thought reasoning.

HFGGUFMLXONNX

Specifications

Property	Value
Parameters	1.2B
Context Length	32K tokens
Architecture	LFM2.5 (Dense)

Math & Logic

Strong arithmetic and logical reasoning

Chain-of-Thought

Step-by-step problem decomposition

Fine-tunable

TRL compatible (SFT, DPO, GRPO)

Quick Start

Transformers

Install:

pip install transformers torch

Download & Run:

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-1.2B-Thinking", device_map="auto")
tokenizer = AutoTokenizer.from_pretrained("LiquidAI/LFM2.5-1.2B-Thinking")

input_ids = tokenizer.apply_chat_template(
    [{"role": "user", "content": "What is 15% of 240?"}],
    add_generation_prompt=True, return_tensors="pt"
).to(model.device)

output = model.generate(input_ids, max_new_tokens=256)
print(tokenizer.decode(output[0], skip_special_tokens=True))

llama.cpp

Install:

brew install llama.cpp
pip install huggingface-hub

Download:

huggingface-cli download LiquidAI/LFM2.5-1.2B-Thinking-GGUF \
  lfm2.5-1.2b-thinking-q4_k_m.gguf --local-dir .

Run:

llama-cli -m lfm2.5-1.2b-thinking-q4_k_m.gguf \
  -p "What is 15% of 240?" -n 256

vLLM

Install:

pip install vllm

Run:

from vllm import LLM, SamplingParams

llm = LLM(model="LiquidAI/LFM2.5-1.2B-Thinking")
output = llm.chat("What is 15% of 240?", SamplingParams(max_tokens=256))
print(output[0].outputs[0].text)