[!WARNING] Disclaimer: This model is provided for evaluation purposes only. Performance, accuracy, and stability may vary. Use at your own discretion.

Description

This is LFM2.5-8B-A1B model converted to the OpenVINO™ IR (Intermediate Representation) format with weights compressed to INT4 by NNCF.

Quantization Parameters

Weight compression was performed using nncf.compress_weights with the following parameters:

mode: INT4_ASYM
group_size: 128
ratio: 1.0

For more information on quantization, check the OpenVINO model optimization guide.

Compatibility

The provided OpenVINO™ IR model is compatible with:

OpenVINO version 2026.3.0 and higher
Optimum Intel 1.27.0 and higher

Running Model Inference with Optimum Intel

Install packages required for using Optimum Intel integration with the OpenVINO backend:

pip install -U "git+https://github.com/huggingface/optimum-intel.git"

As OpenVINO 2026.3.0 is not released yet, install the pre-release (nightly) build of OpenVINO to run this model:

pip install --pre -U openvino --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly

Run model inference:

python

from transformers import AutoTokenizer
from optimum.intel.openvino import OVModelForCausalLM

model_id = "OpenVINO/LFM2.5-8B-A1B-int4-ov"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = OVModelForCausalLM.from_pretrained(model_id)

inputs = tokenizer("What is a capital of France?", return_tensors="pt")

outputs = model.generate(**inputs, max_length=200)
text = tokenizer.batch_decode(outputs)[0]
print(text)

For more examples and possible optimizations, refer to the Inference with Optimum Intel.

Running Model Inference with OpenVINO GenAI

Install packages required for using OpenVINO GenAI.

pip install huggingface_hub
pip install --pre -U openvino openvino-tokenizers openvino-genai --extra-index-url https://storage.openvinotoolkit.org/simple/wheels/nightly

Download model from HuggingFace Hub

python

import huggingface_hub as hf_hub

model_id = "OpenVINO/LFM2.5-8B-A1B-int4-ov"
model_path = "LFM2.5-8B-A1B-int4-ov"

hf_hub.snapshot_download(model_id, local_dir=model_path)

Run model inference:

python

import openvino_genai as ov_genai

device = "CPU"
pipeline_config = {"ATTENTION_BACKEND": "SDPA"}
pipe = ov_genai.LLMPipeline(model_path, device, **pipeline_config)
pipe.get_tokenizer().set_chat_template(pipe.get_tokenizer().chat_template)
print(pipe.generate("What is a capital of France?", max_length=200))

More GenAI usage examples can be found in OpenVINO GenAI library docs and samples

You can find more detailed usage examples in OpenVINO Notebooks:

Limitations

Check the original model card for limitations.

Legal information

The original model is distributed under lfm1.0 license. More details can be found in LFM2.5-8B-A1B.

Disclaimer

Intel is committed to respecting human rights and avoiding causing or contributing to adverse impacts on human rights. See Intel's Global Human Rights Principles. Intel's products and software are intended only to be used in applications that do not cause or contribute to adverse impacts on human rights.