LFM2.5-1.2B-JP-202606

← Back to Text Models LFM2.5-1.2B-JP-202606 is Liquid AI’s general-purpose Japanese chat model. It improves on LFM2.5-1.2B-JP in knowledge, instruction following, math, code, and tool use. It is recommended for agentic workflows, tool use, structured outputs, bilingual English-Japanese assistants, and on-device personal assistants. It is not recommended for knowledge-intensive tasks, and it works best with clear, explicit instructions that define the task, expected behavior, and output format.

HF GGUF MLX ONNX

Specifications

Property	Value
Parameters	1.2B
Context Length	32K tokens
Architecture	LFM2.5 (Dense)
Languages	Japanese, English
Generation Parameters	`temperature=0.1`, `top_k=50`, `repetition_penalty=1.05`

Japanese Chat

Japanese and English assistants

Tool Calling

Native function calling support

Fine-tunable

TRL compatible (SFT, DPO, GRPO)

Quick Start

Transformers
llama.cpp
vLLM
SGLang

Install:

pip install "transformers>=5.2.0" torch accelerate

Download & Run:

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "LiquidAI/LFM2.5-1.2B-JP-202606"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="auto",
    dtype="bfloat16",
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

inputs = tokenizer.apply_chat_template(
    [{"role": "user", "content": "What is machine learning?"}],
    add_generation_prompt=True,
    return_tensors="pt",
    tokenize=True,
    return_dict=True,
).to(model.device)

output = model.generate(**inputs, do_sample=True, temperature=0.1, top_k=50, repetition_penalty=1.05, max_new_tokens=512)
input_length = inputs["input_ids"].shape[1]
response = tokenizer.decode(output[0][input_length:], skip_special_tokens=True)
print(response)

Install:

brew install llama.cpp

Run:

llama-cli -hf LiquidAI/LFM2.5-1.2B-JP-202606-GGUF \
    --temp 0.1 --top-k 50 --repeat-penalty 1.05

The -hf flag downloads the model directly from Hugging Face. For other installation methods and advanced usage, see the llama.cpp guide.

Models

Fine-tuning

Edge Inference

GPU Inference

Cloud Inference

Guides

Help

LFM2.5-1.2B-JP-202606

Specifications

Japanese Chat

Tool Calling

Fine-tunable

Quick Start

​Specifications

Japanese Chat

Tool Calling

Fine-tunable

​Quick Start

Specifications

Quick Start