Instructions to use ovokat/Qwen3-4B-2507-LinuxNerd-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ovokat/Qwen3-4B-2507-LinuxNerd-V1 with Transformers:

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

pipe = pipeline("text-generation", model="ovokat/Qwen3-4B-2507-LinuxNerd-V1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ovokat/Qwen3-4B-2507-LinuxNerd-V1")
model = AutoModelForCausalLM.from_pretrained("ovokat/Qwen3-4B-2507-LinuxNerd-V1", 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 ovokat/Qwen3-4B-2507-LinuxNerd-V1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ovokat/Qwen3-4B-2507-LinuxNerd-V1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ovokat/Qwen3-4B-2507-LinuxNerd-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ovokat/Qwen3-4B-2507-LinuxNerd-V1

SGLang

How to use ovokat/Qwen3-4B-2507-LinuxNerd-V1 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 "ovokat/Qwen3-4B-2507-LinuxNerd-V1" \
    --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": "ovokat/Qwen3-4B-2507-LinuxNerd-V1",
		"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 "ovokat/Qwen3-4B-2507-LinuxNerd-V1" \
        --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": "ovokat/Qwen3-4B-2507-LinuxNerd-V1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ovokat/Qwen3-4B-2507-LinuxNerd-V1 with Docker Model Runner:
```
docker model run hf.co/ovokat/Qwen3-4B-2507-LinuxNerd-V1
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

About:

This is a fine-tune of Qwen3-4B-Instruct-2507 on a dataset consisting entirely of Linux questions and answers curated from a bunch of random public datasets.

For now this is very basic, I'm just testing to see if this'll even work; don't expect anything amazing!

I plan on trying to create some sort of Linux-expert model that can help beginners - this model is not that...

The dataset mostly consists of Qwen3-235B-A22B and GPT-5 responses + a bit of GPT-4.

I'll see about releasing the dataset once it's actually decent.

-- Credit to the Qwen team for making the original model:

@misc{qwen3technicalreport,
      title={Qwen3 Technical Report}, 
      author={Qwen Team},
      year={2025},
      eprint={2505.09388},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2505.09388}, 
}

Downloads last month: 8

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for ovokat/Qwen3-4B-2507-LinuxNerd-V1

Quantizations

1 model

Paper for ovokat/Qwen3-4B-2507-LinuxNerd-V1

Qwen3 Technical Report

Paper • 2505.09388 • Published May 14, 2025 • 343