tg-rising/gemma-3-12b-it-heretic-v2-MLX-VLM-Q6
139
Gemma 3 12B IT Heretic v2 - MLX VLM Q6 (Vision-Capable)
This is a vision-capable 6-bit MLX-converted version of DreamFast/gemma-3-12b-it-heretic-v2.
This model includes vision support for image understanding!
Source Model
- Original Model: DreamFast/gemma-3-12b-it-heretic-v2
- Base Model: google/gemma-3-12b-it
- Model Type: gemma3
- Parameters: 12B
- Includes: Vision tower + Multi-modal projector + Language model
Model Family
This model is part of a complete family with both text-only and vision-capable variants:
Text-Only Variants (mlx-lm)
Vision-Capable Variants (mlx-vlm)
Requirements
pip install -U mlx-vlmUsage - Image Understanding
CLI
# Analyze an image
python -m mlx_vlm.generate \
--model tg-rising/gemma-3-12b-it-heretic-v2-MLX-VLM-Q6 \
--prompt "Describe this image in detail." \
--image /path/to/image.jpg \
--max-tokens 100Python API
from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config
# Load model
model_path = "tg-rising/gemma-3-12b-it-heretic-v2-MLX-VLM-Q6"
model, processor = load(model_path)
config = load_config(model_path)
# Prepare image + text
image = ["/path/to/image.jpg"]
prompt = "What is in this image?"
# Apply chat template
formatted_prompt = apply_chat_template(
processor, config, prompt, num_images=len(image)
)
# Generate
output = generate(model, processor, formatted_prompt, image, max_tokens=100)
print(output)Quantization Details
- Bits: 6-bit
- Mode: affine
- Group Size: 64
- Vision Components: Preserved (not quantized)
- Text Components: 6-bit
License
This model is subject to the Gemma license.