Instructions to use DreamFoundries/Qwen3-VL-4B-Instruct-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DreamFoundries/Qwen3-VL-4B-Instruct-3bit 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("DreamFoundries/Qwen3-VL-4B-Instruct-3bit")
config = load_config("DreamFoundries/Qwen3-VL-4B-Instruct-3bit")

# 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 DreamFoundries/Qwen3-VL-4B-Instruct-3bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "DreamFoundries/Qwen3-VL-4B-Instruct-3bit"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "DreamFoundries/Qwen3-VL-4B-Instruct-3bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use DreamFoundries/Qwen3-VL-4B-Instruct-3bit 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 "DreamFoundries/Qwen3-VL-4B-Instruct-3bit"

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 DreamFoundries/Qwen3-VL-4B-Instruct-3bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use DreamFoundries/Qwen3-VL-4B-Instruct-3bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "DreamFoundries/Qwen3-VL-4B-Instruct-3bit"

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 "DreamFoundries/Qwen3-VL-4B-Instruct-3bit" \
  --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"

Qwen3-VL-4B-Instruct-3bit (repaired)

Re-upload of mlx-community/Qwen3-VL-4B-Instruct-3bit with one fix: the upstream repo ships a stale model.safetensors.index.json describing a 2-shard bf16 checkpoint (model-00001-of-00002.safetensors / model-00002-of-00002.safetensors) that does not exist in that repo — only a single consolidated model.safetensors (3-bit, MLX format, 1219 tensors) is actually present. Any loader that trusts the index blindly (mlx-swift-lm's safetensorWeightURLs, among others) fails trying to open a shard that was never there, and no re-download fixes it since the missing files simply don't exist upstream.

This repo removes the stale index. Weights are otherwise byte-identical to upstream — same single model.safetensors, same digest.

All credit for the conversion to MLX and the 3-bit quantization goes to mlx-community. All credit for the base model goes to the Qwen team (Apache-2.0).

Usage

pip install -U mlx-vlm
python -m mlx_vlm.generate --model DreamFoundries/Qwen3-VL-4B-Instruct-3bit --max-tokens 100 --temperature 0.0 --prompt "Describe this image." --image <path_to_image>

Or open directly in MLXHub on iOS/iPadOS via the badge above.

Downloads last month: 64

Safetensors

Model size

4B params

Tensor type

U32

BF16

MLX

Hardware compatibility

3-bit

Model tree for DreamFoundries/Qwen3-VL-4B-Instruct-3bit

Base model

mlx-community/Qwen3-VL-4B-Instruct-3bit

Quantized

(1)

this model