Instructions to use Gawiiiii/Qwen3-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Gawiiiii/Qwen3-0.6B with Transformers:

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

pipe = pipeline("text-generation", model="Gawiiiii/Qwen3-0.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Gawiiiii/Qwen3-0.6B")
model = AutoModelForCausalLM.from_pretrained("Gawiiiii/Qwen3-0.6B", 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 Gawiiiii/Qwen3-0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Gawiiiii/Qwen3-0.6B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Gawiiiii/Qwen3-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Gawiiiii/Qwen3-0.6B

SGLang

How to use Gawiiiii/Qwen3-0.6B 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 "Gawiiiii/Qwen3-0.6B" \
    --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": "Gawiiiii/Qwen3-0.6B",
		"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 "Gawiiiii/Qwen3-0.6B" \
        --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": "Gawiiiii/Qwen3-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Gawiiiii/Qwen3-0.6B with Docker Model Runner:
```
docker model run hf.co/Gawiiiii/Qwen3-0.6B
```

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Qwen3-0.6B Recovery Scale 0.95

This repository contains a statically merged 0.6B-parameter causal language model based on Qwen3-0.6B. It is a complete Transformers model and does not require PEFT or external adapter files at inference time.

Loading

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "YOUR_USERNAME/YOUR_MODEL_REPOSITORY"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [{"role": "user", "content": "What is 17 + 25?"}]
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=160)
prompt_length = inputs["input_ids"].shape[-1]
print(tokenizer.decode(outputs[0][prompt_length:], skip_special_tokens=True))

Model details

Architecture: Qwen3ForCausalLM
Parameters: 596,049,920
Weight format: Safetensors
Weight files: one statically merged full-model checkpoint
Dynamic adapters required: no

Access to the repository is controlled through the Hugging Face gated-model settings configured by its owner.

Downloads last month: -

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for Gawiiiii/Qwen3-0.6B

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Finetuned

(1149)

this model