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
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
Add oMLX benchmark screenshots
Browse files- .gitattributes +1 -0
- assets/benchmarks/omlx-6bit.png +3 -0
.gitattributes
CHANGED
|
@@ -37,3 +37,4 @@ mlx-8bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 37 |
mlx-6bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
mlx-4bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
assets/benchmarks/omlx-8bit.png filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 37 |
mlx-6bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
mlx-4bit/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
assets/benchmarks/omlx-8bit.png filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
assets/benchmarks/omlx-6bit.png filter=lfs diff=lfs merge=lfs -text
|
assets/benchmarks/omlx-6bit.png
ADDED
|
Git LFS Details
|