Instructions to use qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI

SGLang

How to use qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI with Docker Model Runner:
```
docker model run hf.co/qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI
```

EXAONE-4.0-1.2B-OptAI

EXAONE-4.0 is a large language model series developed by LG AI Research, consisting of a mid-size 32B model optimized for high performance and a small 1.2B model designed for on-device environments.

We have quantized the weights of this model to INT4 (w/o embedding) to optimize it for on-device deployment.

Model Conversion Contributor: Juneyoung Park (OptAI Inc.)

Model Stats:

Input sequence length for Prompt Processor: 128
Maximum context length: 4096
Quantization Type: w4a16 (4-bit weights with 16-bit activations), KV-Cache(INT8)
Supported languages: English, Korean, ...etc
TTFT: Time To First Token is the time it takes to generate the first response token. This is expressed as a range because it varies based on the length of the prompt. The lower bound is for a short prompt (up to 128 tokens, i.e., one iteration of the prompt processor) and the upper bound is for a prompt using the full context length (4096 tokens).
Response Rate: Rate of response generation after the first response token. Measured on a short prompt with a long response; may slow down when using longer context lengths.

Model Details

Type: Causal Language Models
Training Stage: Pretraining & Post-training
Architecture: Transformers with RoPE, QK-Reorder-Norm, and GQA (Grouped Query Attention)
Number of Parameters: 1.2B
Number of Parameters (Non-Embedding): 1.07B
Context Length Support: Up to 4096 tokens (optimized for on-device)

For more details, please refer to the official EXAONE4.0 Blog, GitHub, and Documentation.

Model Performance

Model	Chipset	Target Runtime	Precision	Primary Compute Unit	Context Length	Response Rate (TPS)	Time to First Token (sec)
EXAONE-4.0-1.2B	Snapdragon 8 Elite Mobile	QNN(2.42)-GENIE	W4A16	NPU	4096	55.6	0.04 - 0.9

Model Conversion & Inference

If you want faster inference and conversion support for a wider variety of models, feel free to reach out anytime. When running inference with the uploaded model, we recommend using non-reasoning mode. Please refer to the template below.

[|system|]
{SYSTEM_PROMPT}[|endofturn|]
[|user|]
{USER_PROMPT}[|endofturn|]
[|assistant|]
<think>

</think>

Repository Structure

EXAONE-4.0-1.2B-OptAI/
├── LICENSE
├── README.md
├── .gitattributes
└── EXAONE4.0-1.2B-genie-w4a16-qualcomm_snapdragon_8_elite_OptAI.zip

Internal structure

EXAONE4.0-1.2B-genie-w4a16-qualcomm_snapdragon_8_elite_OptAI/
├── config.json
├── exaone4_part_1_of_5.bin
├── ...
├── exaone4_part_5_of_5.bin
├── genie_config.json
├── tokenizer.json
├── tokenizer_config.json
└── ...

References

License

Source Model: LICENSE
Deployable Model: LICENSE

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI

Base model

LGAI-EXAONE/EXAONE-4.0-1.2B

Quantized

(35)

this model

Paper for qualcomm-ai-hub-community/EXAONE-4.0-1.2B-OptAI

EXAONE 4.0: Unified Large Language Models Integrating Non-reasoning and Reasoning Modes

Paper • 2507.11407 • Published Jul 15, 2025 • 62