Image-Text-to-Text
MLX
Safetensors
gemma4_unified
quantized
gemma
gemma4
apple-silicon
turboquant
4-bit precision
Instructions to use majentik/gemma-4-12B-TurboQuant-MLX-MXFP4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use majentik/gemma-4-12B-TurboQuant-MLX-MXFP4 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("majentik/gemma-4-12B-TurboQuant-MLX-MXFP4") config = load_config("majentik/gemma-4-12B-TurboQuant-MLX-MXFP4") # 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
| { | |
| "bos_token_id": 2, | |
| "do_sample": true, | |
| "eos_token_id": 1, | |
| "pad_token_id": 0, | |
| "suppress_tokens": [ | |
| 255999, | |
| 256000, | |
| 258880, | |
| 258881, | |
| 258882, | |
| 258883 | |
| ], | |
| "temperature": 1.0, | |
| "top_k": 64, | |
| "top_p": 0.95, | |
| "transformers_version": "5.10.0.dev0" | |
| } |