Hellomaniamcoollol/Qwen2.5-Coder-1.5B-Instruct-mlx-fp16

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Sep 18, 2025License:apache-2.0Architecture:Transformer Open Weights Warm

Hellomaniamcoollol/Qwen2.5-Coder-1.5B-Instruct-mlx-fp16 is a 1.5 billion parameter instruction-tuned causal language model, converted to MLX format from the Qwen2.5-Coder-1.5B-Instruct base model developed by Qwen. With a 32768 token context length, this model is specifically designed and optimized for code generation and understanding tasks. Its MLX conversion enables efficient deployment and inference on Apple Silicon hardware.

Loading preview...

Model Overview

This model, Hellomaniamcoollol/Qwen2.5-Coder-1.5B-Instruct-mlx-fp16, is an MLX-converted version of the Qwen2.5-Coder-1.5B-Instruct model, originally developed by Qwen. It features 1.5 billion parameters and supports a substantial context length of 32768 tokens, making it suitable for handling extensive codebases or complex programming prompts.

Key Characteristics

  • Code-Optimized: The "Coder" designation indicates its primary focus and fine-tuning for code-related tasks, including generation, completion, and understanding.
  • Instruction-Tuned: As an "Instruct" model, it is designed to follow natural language instructions effectively, making it user-friendly for developers.
  • MLX Format: Converted using mlx-lm version 0.26.4, this model is optimized for performance on Apple Silicon, offering efficient local inference capabilities.
  • Parameter Efficiency: At 1.5 billion parameters, it strikes a balance between performance and computational resource requirements, making it accessible for various development environments.

Use Cases

This model is particularly well-suited for:

  • Code Generation: Generating code snippets, functions, or entire scripts based on natural language descriptions.
  • Code Completion: Assisting developers with intelligent code suggestions within an IDE-like environment.
  • Code Explanation: Providing explanations for existing code, aiding in understanding complex logic.
  • Educational Tools: Serving as a backend for programming tutors or learning platforms.
  • Local Development: Ideal for developers working on Apple Silicon devices who require a capable code model for local inference without cloud dependencies.

Finetunes
1 models