ssdataanalysis/DictaLM-3.0-1.7B-Thinking-mlx-fp16

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:Feb 5, 2026License:apache-2.0Architecture:Transformer Open Weights Warm

The ssdataanalysis/DictaLM-3.0-1.7B-Thinking-mlx-fp16 model is a 1.7 billion parameter language model, converted to MLX format from dicta-il/DictaLM-3.0-1.7B-Thinking. This model is designed for efficient deployment and inference on Apple Silicon, leveraging the MLX framework. Its primary utility lies in providing a compact yet capable language model for local execution and development within the MLX ecosystem.

Loading preview...

Model Overview

The ssdataanalysis/DictaLM-3.0-1.7B-Thinking-mlx-fp16 is a 1.7 billion parameter language model, specifically adapted for the MLX framework. This model is a converted version of the original dicta-il/DictaLM-3.0-1.7B-Thinking model, optimized for performance on Apple Silicon hardware.

Key Characteristics

  • Parameter Count: 1.7 billion parameters, offering a balance between performance and resource efficiency.
  • MLX Format: Converted using mlx-lm version 0.29.1, ensuring compatibility and optimized execution on MLX-supported devices.
  • Origin: Derived from the dicta-il/DictaLM-3.0-1.7B-Thinking base model.

Usage

This model is intended for developers and researchers working within the MLX ecosystem. It can be easily loaded and used for text generation tasks using the mlx-lm library. The provided code snippets demonstrate how to load the model and tokenizer, and generate responses from a given prompt, including support for chat templates if available.

Good For

  • Local Inference: Ideal for running language model tasks directly on Apple Silicon devices.
  • MLX Development: A suitable model for experimenting with and developing applications using the MLX framework.
  • Resource-Constrained Environments: Its relatively small size makes it a good choice for scenarios where larger models are impractical.