Instructions to use TerminatorPower/Qwen3-VL-4B-Thinking-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use TerminatorPower/Qwen3-VL-4B-Thinking-4bit with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("TerminatorPower/Qwen3-VL-4B-Thinking-4bit") config = load_config("TerminatorPower/Qwen3-VL-4B-Thinking-4bit") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use TerminatorPower/Qwen3-VL-4B-Thinking-4bit with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "TerminatorPower/Qwen3-VL-4B-Thinking-4bit"
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "TerminatorPower/Qwen3-VL-4B-Thinking-4bit" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use TerminatorPower/Qwen3-VL-4B-Thinking-4bit with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "TerminatorPower/Qwen3-VL-4B-Thinking-4bit"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default TerminatorPower/Qwen3-VL-4B-Thinking-4bit
Run Hermes
hermes
Qwen3-VL-4B-Thinking-4bit
A verbatim mirror of mlx-community/Qwen3-VL-4B-Thinking-4bit, kept here so the Vanta iOS app always has a stable place to download it from.
Run it on your iPhone with Vanta
This is one of the built-in one-tap downloads in Vanta - Local AI LLM Chat, a local-first AI chat app for iPhone and iPad. Vanta runs models like this one fully on-device with Apple's MLX framework - no account and no cloud, your chats stay on your device. Because it's a vision-capable model, you can also chat about images.
Download Vanta on the App Store ->
This is a copy. Every model file in this repository is an exact copy of
mlx-community/Qwen3-VL-4B-Thinking-4bit. We cloned it so that Vanta Client always has a reliable, always-available source to download this model from, independent of any upstream changes. All credit for the model weights and the MLX conversion goes to mlx-community, Qwen, and the original authors.
Model Details
- Original Model: Qwen/Qwen3-VL-4B-Thinking
- Upstream MLX Repo: mlx-community/Qwen3-VL-4B-Thinking-4bit
- Quantization: 4-bit
- Format: MLX SafeTensors
- Framework: mlx-vlm
- Model Type:
qwen3_vl - Task: Image-text-to-text
- Disk Size: ~3.1 GB
Conversion Details
The upstream model was converted to MLX format from
Qwen/Qwen3-VL-4B-Thinking
using mlx-vlm version 0.3.4.
Related Models
- Lower-RAM Vanta fallback: TerminatorPower/Qwen3-VL-2B-Instruct-4bit
- Upstream MLX repo: mlx-community/Qwen3-VL-4B-Thinking-4bit
- Original: Qwen/Qwen3-VL-4B-Thinking
Usage
from mlx_vlm import load, generate
model, processor = load("TerminatorPower/Qwen3-VL-4B-Thinking-4bit")
output = generate(
model,
processor,
prompt="Describe this image.",
image="path/to/image.jpg",
max_tokens=512
)
print(output)
CLI:
python3 -m mlx_vlm.generate \
--model TerminatorPower/Qwen3-VL-4B-Thinking-4bit \
--image path/to/image.jpg \
--prompt "Describe this image."
License
This model inherits the Apache 2.0 license from the original Qwen model. The mirror does not add any restrictions.
- Downloads last month
- 5
4-bit
Model tree for TerminatorPower/Qwen3-VL-4B-Thinking-4bit
Base model
Qwen/Qwen3-VL-4B-Thinking