Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

chanderbalaji
/
Grug-12B-VLM-MLX

Image-Text-to-Text
Safetensors
MLX
mlx-vlm
gemma4_unified
gemma-4
vision-language
quantized
4-bit precision
6-bit
8-bit precision
apple-silicon
Model card Files Files and versions
xet
Community

Instructions to use chanderbalaji/Grug-12B-VLM-MLX with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

  • Libraries
  • MLX

    How to use chanderbalaji/Grug-12B-VLM-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("chanderbalaji/Grug-12B-VLM-MLX")
    config = load_config("chanderbalaji/Grug-12B-VLM-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
Grug-12B-VLM-MLX / mlx-8bit
12.7 GB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1 commit
chanderbalaji's picture
chanderbalaji
Upload mlx-8bit MLX quant
db6e1a0 verified 5 days ago
  • chat_template.jinja
    17.5 kB
    Upload mlx-8bit MLX quant 5 days ago
  • config.json
    5.79 kB
    Upload mlx-8bit MLX quant 5 days ago
  • generation_config.json
    255 Bytes
    Upload mlx-8bit MLX quant 5 days ago
  • model-00001-of-00003.safetensors
    5.35 GB
    xet
    Upload mlx-8bit MLX quant 5 days ago
  • model-00002-of-00003.safetensors
    5.36 GB
    xet
    Upload mlx-8bit MLX quant 5 days ago
  • model-00003-of-00003.safetensors
    2.01 GB
    xet
    Upload mlx-8bit MLX quant 5 days ago
  • model.safetensors.index.json
    135 kB
    Upload mlx-8bit MLX quant 5 days ago
  • processor_config.json
    868 Bytes
    Upload mlx-8bit MLX quant 5 days ago
  • tokenizer.json
    32.2 MB
    xet
    Upload mlx-8bit MLX quant 5 days ago
  • tokenizer_config.json
    2.75 kB
    Upload mlx-8bit MLX quant 5 days ago
  • training_summary.json
    2.16 kB
    Upload mlx-8bit MLX quant 5 days ago