Favorite Models
Collection
Models with that certain something. Non-exhaustive list, no particular order. • 19 items • Updated • 5
- Downloads last month
- 31
Model size
11B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
8-bit
Model tree for McG-221/Blossom-V6.4-35B-A3B-9bit
Base model
Qwen/Qwen3.5-35B-A3B-Base Finetuned
Azure99/Blossom-V6.4-35B-A3B
# 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("McG-221/Blossom-V6.4-35B-A3B-9bit") config = load_config("McG-221/Blossom-V6.4-35B-A3B-9bit") # 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)