Instructions to use develoco/Qwen3-4B-LayerBoost with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use develoco/Qwen3-4B-LayerBoost with Transformers:

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

pipe = pipeline("text-generation", model="develoco/Qwen3-4B-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("develoco/Qwen3-4B-LayerBoost", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("develoco/Qwen3-4B-LayerBoost", trust_remote_code=True)
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 develoco/Qwen3-4B-LayerBoost with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "develoco/Qwen3-4B-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": "develoco/Qwen3-4B-LayerBoost",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/develoco/Qwen3-4B-LayerBoost

SGLang

How to use develoco/Qwen3-4B-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 "develoco/Qwen3-4B-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": "develoco/Qwen3-4B-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 "develoco/Qwen3-4B-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": "develoco/Qwen3-4B-LayerBoost",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use develoco/Qwen3-4B-LayerBoost with Docker Model Runner:
```
docker model run hf.co/develoco/Qwen3-4B-LayerBoost
```

Qwen3-4B-LayerBoost / README.md

develoco

Duplicate from openchip-sw/Qwen3-4B-LayerBoost

9e4828b about 1 month ago

preview code

Raw

History Blame Contribute Delete

1.74 kB

	---
	library_name: transformers
	---
	# Qwen3-4B-hybrid-OC

	A hybrid model developed by Openchip by applying proprietary linearization approach LayerBoost to the Qwen3-4B, reducing latency and increasing token throughtput by 68%.

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

	## Setup

	Before using this model, install the following system dependencies:

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

	After that, install the requirements
	```bash
	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
	```bash
	hf auth login
	```
	### Use the model
	```python
	from transformers import AutoModelForCausalLM, AutoTokenizer, AutoConfig
	import torch

	model_id = "openchip-sw/Qwen3-4B-LayerBoost"

	device = "cuda" if torch.cuda.is_available() else "cpu"

	config = AutoConfig.from_pretrained(model_id)
	tokenizer = AutoTokenizer.from_pretrained(model_id)
	model = AutoModelForCausalLM.from_pretrained(
	model_id,
	trust_remote_code=True,
	)

	model.eval()
	model.to(device)

	prompt = "give me the list of European countrie accompanied with the capitals"

	eval_inputs = tokenizer(prompt, return_tensors="pt")
	eval_inputs = {k: v.to(device) for k, v in eval_inputs.items()}
	eval_tokens = model.generate(
	**eval_inputs,
	max_new_tokens=512,
	do_sample=False,
	use_cache=True,
	return_dict_in_generate=True,
	)

	out_text = tokenizer.decode(eval_tokens.sequences[0], skip_special_tokens=True)
	print("Generated text:", out_text)
	```