Instructions to use NexaAI/qwen3vl-4B-Thinking-4bit-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use NexaAI/qwen3vl-4B-Thinking-4bit-mlx 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("NexaAI/qwen3vl-4B-Thinking-4bit-mlx")
config = load_config("NexaAI/qwen3vl-4B-Thinking-4bit-mlx")

# 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

How to use NexaAI/qwen3vl-4B-Thinking-4bit-mlx with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "NexaAI/qwen3vl-4B-Thinking-4bit-mlx"

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": "NexaAI/qwen3vl-4B-Thinking-4bit-mlx"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use NexaAI/qwen3vl-4B-Thinking-4bit-mlx 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 "NexaAI/qwen3vl-4B-Thinking-4bit-mlx"

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 NexaAI/qwen3vl-4B-Thinking-4bit-mlx

Run Hermes

hermes

OpenClaw new

How to use NexaAI/qwen3vl-4B-Thinking-4bit-mlx with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "NexaAI/qwen3vl-4B-Thinking-4bit-mlx"

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "NexaAI/qwen3vl-4B-Thinking-4bit-mlx" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Configuration Parsing Warning:Invalid JSON for config file config.json

Qwen3-VL-4B-Thinking

Run Qwen3-VL-4B-Thinking optimized for Apple Silicon on MLX with NexaSDK.

Quickstart

Install NexaSDK

Run the model locally with one line of code:

nexa infer NexaAI/qwen3vl-4B-Thinking-4bit-mlx

Model Description

Qwen3-VL-4B-Thinking is a 4-billion-parameter multimodal large language model from the Qwen team at Alibaba Cloud.
Part of the Qwen3-VL (Vision-Language) family, it is designed for advanced visual reasoning and chain-of-thought generation across image, text, and video inputs.

Compared to the Instruct variant, the Thinking model emphasizes deeper multi-step reasoning, analysis, and planning. It produces detailed, structured outputs that reflect intermediate reasoning steps, making it well-suited for research, multimodal understanding, and agentic workflows.

Features

Vision-Language Understanding: Processes images, text, and videos for joint reasoning tasks.
Structured Thinking Mode: Generates intermediate reasoning traces for better transparency and interpretability.
High Accuracy on Visual QA: Performs strongly on visual question answering, chart reasoning, and document analysis benchmarks.
Multilingual Support: Understands and responds in multiple languages.
Optimized for Efficiency: Delivers strong performance at 4B scale for on-device or edge deployment.

Use Cases

Multimodal reasoning and visual question answering
Scientific and analytical reasoning tasks involving charts, tables, and documents
Step-by-step visual explanation or tutoring
Research on interpretability and chain-of-thought modeling
Integration into agent systems that require structured reasoning

Inputs and Outputs

Input:

Text, images, or combined multimodal prompts (e.g., image + question)

Output:

Generated text, reasoning traces, or structured responses
May include explicit thought steps or structured JSON reasoning sequences

License

Check the official Qwen license for terms of use and redistribution.

Downloads last month: 12

MLX

Hardware compatibility

Quantized

Model tree for NexaAI/qwen3vl-4B-Thinking-4bit-mlx

Base model

Qwen/Qwen3-VL-4B-Thinking

Finetuned

(23)

this model

Collection including NexaAI/qwen3vl-4B-Thinking-4bit-mlx

Qwen3VL

Collection

Nexa AI infra to support Qwen3VL running on GPU/NPU/CPU • 21 items • Updated Mar 2 • 4