ailexleon/Anubis-Mini-8B-v1-mlx-fp16

TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Mar 13, 2026Architecture:Transformer Cold

Anubis-Mini-8B-v1-mlx-fp16 is an 8 billion parameter language model, converted by ailexleon to the MLX format for efficient deployment on Apple Silicon. This model is a version of TheDrummer's Anubis-Mini-8B-v1, specifically optimized for local inference with MLX. It provides a compact yet capable solution for various natural language processing tasks on compatible hardware.

Loading preview...

Overview

This model, ailexleon/Anubis-Mini-8B-v1-mlx-fp16, is an 8 billion parameter language model. It is a conversion of the original TheDrummer/Anubis-Mini-8B-v1 model into the MLX format, specifically designed for efficient execution on Apple Silicon. The conversion was performed using mlx-lm version 0.29.1, ensuring compatibility and optimized performance for local inference.

Key Capabilities

  • MLX Optimization: Specifically formatted for Apple Silicon, enabling efficient local inference.
  • 8 Billion Parameters: Offers a balance between model size and performance for various NLP tasks.
  • Easy Integration: Provides clear instructions and Python code snippets for loading and generating text using the mlx-lm library.

Use Cases

This model is particularly well-suited for developers and researchers looking to:

  • Run language model inference directly on Apple Silicon devices.
  • Experiment with an 8B parameter model in an optimized local environment.
  • Integrate a capable language model into applications leveraging the MLX ecosystem.