Instructions to use Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128 with Transformers:

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

pipe = pipeline("text-generation", model="Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128")
model = AutoModelForCausalLM.from_pretrained("Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128

SGLang

How to use Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128 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 "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128 with Docker Model Runner:
```
docker model run hf.co/Hyun9junn/K-EXAONE-236B-A23B-W4A16-G128
```

Hyun9junn commited on Apr 13

Commit

a81f41b

verified ·

1 Parent(s): 5e04abe

Update README.md

Browse files

Files changed (1) hide show

README.md +4 -6

README.md CHANGED Viewed

@@ -16,8 +16,8 @@ base_model: LGAI-EXAONE/K-EXAONE-236B-A23B
 ---
 # K-EXAONE-236B-A23B-W4A16-G128
-### 🔄 (2026-04-13) v2 Update - Improved Quantization (# of Calibration Dataset 512, Sequence len 512)
-### 🔄 (2026-04-10) Initial commit (# of Calibration Dataset 32, Sequence len 128)
 > **Note — Early release**
 >
@@ -63,6 +63,8 @@ This is the **first W4A16 AWQ checkpoint** for K-EXAONE-236B-A23B publicly avail
 Quantization was performed using [llm-compressor](https://github.com/vllm-project/llm-compressor) with a **MoE-aware AWQ** recipe.
 **Method:** AWQ applies channel-wise scaling to minimize quantization error by protecting salient weights, using a calibration dataset to determine optimal scales.
 **Recipe highlights:**
@@ -75,8 +77,6 @@ Quantization was performed using [llm-compressor](https://github.com/vllm-projec
 * Layer 0 (dense MLP) and `lm_head` are excluded from quantization
 * Gate weight tensors are excluded from quantization
-The full recipe is available in `recipe.yaml`. The MoE-aware AWQ recipe was developed in [SqueezeBits/EXAONE](https://github.com/SqueezeBits/EXAONE).
 **Calibration dataset:** [`neuralmagic/LLM_compression_calibration`](https://huggingface.co/datasets/neuralmagic/LLM_compression_calibration) (512 samples, sequence length 2048)
 ---
@@ -241,5 +241,3 @@ If you use this model, please cite the original K-EXAONE work:
   url    = {https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B}
 }
 ```
-Quantization produced by [Hyun9junn](https://huggingface.co/Hyun9junn) using [llm-compressor](https://github.com/vllm-project/llm-compressor).

 ---
 # K-EXAONE-236B-A23B-W4A16-G128
+**🔄 (2026-04-13) Improved Quantization** - scale-up calibration dataset (# of Calibration Dataset 512, Sequence len 512)
+**🔄 (2026-04-10) Initial commit** (# of Calibration Dataset 32, Sequence len 128)
 > **Note — Early release**
 >
 Quantization was performed using [llm-compressor](https://github.com/vllm-project/llm-compressor) with a **MoE-aware AWQ** recipe.
+The EXAONE specific MoE-aware AWQ recipe was developed in [SqueezeBits/llm-compressor-K-EXAONE](https://github.com/SqueezeBits/llm-compressor-K-EXAONE).
 **Method:** AWQ applies channel-wise scaling to minimize quantization error by protecting salient weights, using a calibration dataset to determine optimal scales.
 **Recipe highlights:**
 * Layer 0 (dense MLP) and `lm_head` are excluded from quantization
 * Gate weight tensors are excluded from quantization
 **Calibration dataset:** [`neuralmagic/LLM_compression_calibration`](https://huggingface.co/datasets/neuralmagic/LLM_compression_calibration) (512 samples, sequence length 2048)
 ---
   url    = {https://huggingface.co/LGAI-EXAONE/K-EXAONE-236B-A23B}
 }
 ```