Instructions to use openchip-sw/Qwen3-8B-LayerBoost with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use openchip-sw/Qwen3-8B-LayerBoost with Transformers:

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

pipe = pipeline("text-generation", model="openchip-sw/Qwen3-8B-LayerBoost", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("openchip-sw/Qwen3-8B-LayerBoost", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("openchip-sw/Qwen3-8B-LayerBoost", trust_remote_code=True, device_map="auto")
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 openchip-sw/Qwen3-8B-LayerBoost with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "openchip-sw/Qwen3-8B-LayerBoost"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "openchip-sw/Qwen3-8B-LayerBoost",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/openchip-sw/Qwen3-8B-LayerBoost

SGLang

How to use openchip-sw/Qwen3-8B-LayerBoost 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 "openchip-sw/Qwen3-8B-LayerBoost" \
    --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": "openchip-sw/Qwen3-8B-LayerBoost",
		"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 "openchip-sw/Qwen3-8B-LayerBoost" \
        --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": "openchip-sw/Qwen3-8B-LayerBoost",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use openchip-sw/Qwen3-8B-LayerBoost with Docker Model Runner:
```
docker model run hf.co/openchip-sw/Qwen3-8B-LayerBoost
```

Qwen3-8B-hybrid-OC

A hybrid model developed by Openchip by applying proprietary linearization approach LayerBoost to the Qwen3-8B.

Details about LayerBoost approach are available on arXiv: https://arxiv.org/pdf/2604.22050v2

Setup

Before using this model, install the following system dependencies:

apt-get update
apt-get install -y --no-install-recommends \
    build-essential

After that, install the requirements

transformers==4.56.2
accelerate==1.11.0
peft==0.18.0
torch==2.10
flash-attn @ https://github.com/mjun0812/flash-attention-prebuild-wheels/releases/download/v0.7.12/flash_attn-2.8.3+cu128torch2.10-cp312-cp312-linux_x86_64.whl

Example Usage

Login to Huggigface

hf auth login

Use the model

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_id = "openchip-sw/Qwen3-8B-LayerBoost"

if not torch.cuda.is_available():
    raise RuntimeError("CUDA GPU is required")

tokenizer = AutoTokenizer.from_pretrained(model_id)

model = AutoModelForCausalLM.from_pretrained(
    model_id,
    trust_remote_code=True,
    device_map={"": "cuda:0"},  # Load directly onto GPU 0
    torch_dtype=torch.bfloat16,  # Use float16 if your GPU lacks BF16 support
    low_cpu_mem_usage=True,
)

model.eval()

prompt = (
    "Give me a list of European countries accompanied by their capitals."
)

eval_inputs = tokenizer(prompt, return_tensors="pt").to("cuda:0")

with torch.inference_mode():
    eval_tokens = model.generate(
        **eval_inputs,
        max_new_tokens=128,
        do_sample=False,
        use_cache=True,
    )

generated_tokens = eval_tokens[0, eval_inputs["input_ids"].shape[1]:]
out_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)

print("Generated text:", out_text)

Downloads last month: 362

Safetensors

Model size

8B params

Tensor type

BF16

Paper for openchip-sw/Qwen3-8B-LayerBoost

LayerBoost: Layer-Aware Attention Reduction for Efficient LLMs

Paper • 2604.22050 • Published May 14