Instructions to use CarlOwOs/Qwen3-0.6B-Base-int2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CarlOwOs/Qwen3-0.6B-Base-int2 with Transformers:

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

pipe = pipeline("text-generation", model="CarlOwOs/Qwen3-0.6B-Base-int2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("CarlOwOs/Qwen3-0.6B-Base-int2")
model = AutoModelForMultimodalLM.from_pretrained("CarlOwOs/Qwen3-0.6B-Base-int2")
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 CarlOwOs/Qwen3-0.6B-Base-int2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CarlOwOs/Qwen3-0.6B-Base-int2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CarlOwOs/Qwen3-0.6B-Base-int2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CarlOwOs/Qwen3-0.6B-Base-int2

SGLang

How to use CarlOwOs/Qwen3-0.6B-Base-int2 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 "CarlOwOs/Qwen3-0.6B-Base-int2" \
    --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": "CarlOwOs/Qwen3-0.6B-Base-int2",
		"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 "CarlOwOs/Qwen3-0.6B-Base-int2" \
        --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": "CarlOwOs/Qwen3-0.6B-Base-int2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CarlOwOs/Qwen3-0.6B-Base-int2 with Docker Model Runner:
```
docker model run hf.co/CarlOwOs/Qwen3-0.6B-Base-int2
```

Qwen3-0.6B-Base Quantized (INT2)

This model is a quantized version of Qwen/Qwen3-0.6B-Base using optimum-quanto with int2 weight quantization.

Model Details

Base Model: Qwen/Qwen3-0.6B-Base
Quantization: int2 weights using optimum-quanto
Library: Transformers + Optimum-Quanto

Usage

You can load and use this quantized model directly:

from transformers import AutoTokenizer, AutoModelForCausalLM
from optimum.quanto import QuantizedModelForCausalLM

# Load tokenizer and model directly
tokenizer = AutoTokenizer.from_pretrained("CarlOwOs/Qwen3-0.6B-Base-int2", trust_remote_code=True)
model = QuantizedModelForCausalLM.from_pretrained("CarlOwOs/Qwen3-0.6B-Base-int2")

# Generate text
inputs = tokenizer("Hello, how are you?", return_tensors="pt")
outputs = model.generate(**inputs, max_length=50, do_sample=True, temperature=0.7)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Alternative Loading Method

# If the direct method doesn't work, try this:
from transformers import AutoTokenizer
from optimum.quanto import QuantizedModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CarlOwOs/Qwen3-0.6B-Base-int2", trust_remote_code=True)
model = QuantizedModelForCausalLM.from_pretrained("CarlOwOs/Qwen3-0.6B-Base-int2")

# Use the model for inference
inputs = tokenizer("What is the capital of France?", return_tensors="pt")
with torch.no_grad():
    outputs = model.generate(
        **inputs, 
        max_length=100, 
        do_sample=True, 
        temperature=0.7,
        pad_token_id=tokenizer.eos_token_id
    )
generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(generated_text)

Performance

This quantized model provides significant memory savings compared to the original model:

Inference Speed: Similar to original model
Quality: Maintains good performance for most tasks

Technical Details

Quantization Method: optimum-quanto int2 weight quantization
Base Model: Qwen/Qwen3-0.6B-Base
Precision: int2 weights, float16 activations

License

Same as the base model license.

Downloads last month: 2

Safetensors

Model size

0.3B params

Tensor type

F16

Model tree for CarlOwOs/Qwen3-0.6B-Base-int2

Base model

Qwen/Qwen3-0.6B-Base

Finetuned

(609)

this model