Instructions to use Cormac315/Qwen3-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Cormac315/Qwen3-0.6B with Transformers:

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

pipe = pipeline("text-generation", model="Cormac315/Qwen3-0.6B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Cormac315/Qwen3-0.6B")
model = AutoModelForCausalLM.from_pretrained("Cormac315/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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Cormac315/Qwen3-0.6B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Cormac315/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": "Cormac315/Qwen3-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Cormac315/Qwen3-0.6B

SGLang

How to use Cormac315/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 "Cormac315/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": "Cormac315/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 "Cormac315/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": "Cormac315/Qwen3-0.6B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Cormac315/Qwen3-0.6B with Docker Model Runner:
```
docker model run hf.co/Cormac315/Qwen3-0.6B
```

You need to agree to share your Hugging Face 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

This is a merged, directly loadable Qwen3-0.6B model fine-tuned with LoRA and exported as a complete Transformers model. It is not a standalone LoRA adapter.

Load with Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "Cormac315/Qwen3-0.6B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, 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=128)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

For a private repository, log in first with hf auth login or pass a Hugging Face token to from_pretrained.

Evaluation summary

All scores below use the same frozen thinking-mode evaluation contract for each paired comparison.

Model	Safety	Basic + medium Math	General	Weighted score
Qwen3-0.6B base	68.75%	26.67%	56.67%	52.50%
This model	81.25%	23.11%	54.64%	55.83%

The weighted score is 0.40 × Safety + 0.30 × Math + 0.30 × General. This checkpoint was selected as the highest weighted fallback model; it is not an all-domain statistically significant winner.

Model identity

Base model: Qwen/Qwen3-0.6B
Format: merged full model in Safetensors
Weight file SHA-256: 0167f55b6f3b23f045a65322371e6d3afd383e400b18b9a5ce70fedecbbf7be3
Complete local model directory SHA-256: 38d7f7e3baed33665f3838f2c3e0e840a153780801494e200f1afcdc05ad975c

Downloads last month: 4

Safetensors

Model size

0.6B params

Tensor type

BF16

Model tree for Cormac315/Qwen3-0.6B

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

Qwen/Qwen3-0.6B

Adapter

(687)

this model