ligaments-dev/Qwen2.5-1.5B-Instruct-itr-lora
TEXT GENERATIONConcurrency Cost:1Model Size:1.5BQuant:BF16Ctx Length:32kPublished:Apr 30, 2026License:apache-2.0Architecture:Transformer Open Weights Warm
The ligaments-dev/Qwen2.5-1.5B-Instruct-itr-lora is a 1.5 billion parameter instruction-tuned causal language model, converted to MLX format from the Qwen/Qwen2.5-1.5B-Instruct base model. This model is designed for efficient deployment and inference within the MLX ecosystem, leveraging its 32768 token context length. It is primarily suited for general instruction-following tasks and applications requiring a compact yet capable language model.
Loading preview...
ligaments-dev/Qwen2.5-1.5B-Instruct-itr-lora Overview
This model is an MLX-format conversion of the Qwen2.5-1.5B-Instruct model, originally developed by Qwen. With 1.5 billion parameters and a substantial 32,768 token context length, it is optimized for efficient performance within the Apple MLX framework.
Key Capabilities
- Instruction Following: Designed to understand and execute a wide range of user instructions.
- MLX Compatibility: Fully converted and ready for use with the
mlx-lmlibrary, enabling streamlined deployment on Apple silicon. - Compact Size: Its 1.5 billion parameters make it suitable for applications where computational resources or inference speed are critical.
- Extended Context: Benefits from the base model's 32,768 token context window, allowing for processing longer inputs and maintaining conversational coherence over extended interactions.
Good For
- Developers working with Apple silicon who need a readily available, instruction-tuned language model.
- Applications requiring a balance between model capability and efficient local inference.
- General-purpose text generation, summarization, and question-answering tasks where a smaller model footprint is advantageous.