Instructions to use Kwai-Klear/Klear-46B-A2.5B-Base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Kwai-Klear/Klear-46B-A2.5B-Base with Transformers:

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

pipe = pipeline("text-generation", model="Kwai-Klear/Klear-46B-A2.5B-Base", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Kwai-Klear/Klear-46B-A2.5B-Base", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Kwai-Klear/Klear-46B-A2.5B-Base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Kwai-Klear/Klear-46B-A2.5B-Base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Kwai-Klear/Klear-46B-A2.5B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Kwai-Klear/Klear-46B-A2.5B-Base

SGLang

How to use Kwai-Klear/Klear-46B-A2.5B-Base 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 "Kwai-Klear/Klear-46B-A2.5B-Base" \
    --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": "Kwai-Klear/Klear-46B-A2.5B-Base",
		"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 "Kwai-Klear/Klear-46B-A2.5B-Base" \
        --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": "Kwai-Klear/Klear-46B-A2.5B-Base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Kwai-Klear/Klear-46B-A2.5B-Base with Docker Model Runner:
```
docker model run hf.co/Kwai-Klear/Klear-46B-A2.5B-Base
```

tech report link broken

by eliebak - opened Sep 5, 2025

Discussion

eliebak

Sep 5, 2025

Congrats on the release, the model looks super nice. You're probably aware of it, but just in case, the tech report link is redirecting to hf model page

BubbleQ

Klear team, Kuaishou Technology org Sep 6, 2025

Thank you for your kind words and for pointing that out! Our tech report is still in progress — we’ll update the link once it’s published.

eliebak changed discussion status to closed Sep 6, 2025

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