Instructions to use TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE with Transformers:

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

pipe = pipeline("text-generation", model="TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE")
model = AutoModelForCausalLM.from_pretrained("TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE", 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 TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE

SGLang

How to use TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE 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 "TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE" \
    --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": "TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE",
		"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 "TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE" \
        --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": "TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE with Docker Model Runner:
```
docker model run hf.co/TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Qwen3 4B Thinking x Gemini 3 Flash VIBE

This model was trained on 200 agentic coding examples generated by gemini 3 flash preview.

For more info on how and what the model was trained on, please view the dataset card

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 39

Safetensors

Model size

4B params

Tensor type

BF16

Model tree for TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE

Base model

Qwen/Qwen3-4B-Thinking-2507

Finetuned

unsloth/Qwen3-4B-Thinking-2507

Finetuned

(107)

this model

Merges

1 model

Quantizations

1 model

TeichAI
/

Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE

Qwen3 4B Thinking x Gemini 3 Flash VIBE

Model tree for TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE

Dataset used to train TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE