Instructions to use naver-hyperclovax/HyperCLOVAX-SEED-Think-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-32B with Transformers:

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

pipe = pipeline("text-generation", model="naver-hyperclovax/HyperCLOVAX-SEED-Think-32B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("naver-hyperclovax/HyperCLOVAX-SEED-Think-32B", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "naver-hyperclovax/HyperCLOVAX-SEED-Think-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "naver-hyperclovax/HyperCLOVAX-SEED-Think-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-32B

SGLang

How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-32B 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 "naver-hyperclovax/HyperCLOVAX-SEED-Think-32B" \
    --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": "naver-hyperclovax/HyperCLOVAX-SEED-Think-32B",
		"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 "naver-hyperclovax/HyperCLOVAX-SEED-Think-32B" \
        --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": "naver-hyperclovax/HyperCLOVAX-SEED-Think-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use naver-hyperclovax/HyperCLOVAX-SEED-Think-32B with Docker Model Runner:
```
docker model run hf.co/naver-hyperclovax/HyperCLOVAX-SEED-Think-32B
```

Can I run this with vLLM?

by DrXaviere - opened Dec 29, 2025

Discussion

DrXaviere

Dec 29, 2025

Can I run this with vLLM?
Also, I have A100 80gb x 2.
In requirement section, I need 4 of those, but as the model is 32B, I guess one A100 80gb might be fine.

kaki-paper

Dec 29, 2025

https://github.com/vllm-project/vllm/pull/31471

I am currently working on it :)

and I guess you can probably run this model with A100 80gb x 2.

appleeji

Dec 29, 2025

If you use Omniserve, the vision encoder and the LLM run as separate services, so you need to cap vLLM’s GPU memory usage. By default vLLM will try to use almost all available GPU memory, so on 2× A100 80GB I’d run the 32B model with tensor parallelism 2 and set --gpu-memory-utilization to around 0.7. That way you leave some headroom on each GPU and can still run the vision encoder on the same GPUs.
(https://github.com/NAVER-Cloud-HyperCLOVA-X/OmniServe)

lesj0610

Jan 4

This comment has been hidden (marked as Off-Topic)

pathosethoslogos

Jan 8

https://github.com/vllm-project/vllm/pull/31471

I am currently working on it :)

and I guess you can probably run this model with A100 80gb x 2.

What about Nvidia Spark - Docker - vLLM?

kaki-paper

Jan 9

As long as you have more than 80gb vram, it should be fine I guess :)

kaki-paper

Jan 10

https://github.com/vllm-project/vllm/pull/31471

I've been working on adding support for text input and image+text input for this model. It hasn't been reviewed yet, so I'm not sure when it will be merged, but if you need it, feel free to download vLLM based on this PR and use it.

If you find any bugs, please let me know and I'll fix them right away!

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment