Kimi K2.6
See Kimi K2.6 in action: demonstration video
Full-quality MLX conversion of Kimi-K2.6 for use with Inferencer app's distributed compute or model streaming features.
NOTICE - Moved to archive due to storage restrictions: available here
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for inferencerlabs/archived-Kimi-K2.6-MLX
Base model
moonshotai/Kimi-K2.6
# 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("inferencerlabs/archived-Kimi-K2.6-MLX") config = load_config("inferencerlabs/archived-Kimi-K2.6-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)