mstyslavity/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16

VISIONConcurrency Cost:2Model Size:27BQuant:FP8Ctx Length:32kPublished:Jun 5, 2026License:gemmaArchitecture:Transformer Cold

MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16 is a 27 billion parameter instruction-tuned language model, converted to the MLX format by mstyslavity from the original INSAIT-Institute model. This model is optimized for efficient deployment and inference on Apple silicon, leveraging the MLX framework. It is designed for general-purpose conversational AI and instruction following tasks, providing a robust foundation for various natural language processing applications.

Loading preview...

Overview

This model, mstyslavity/MamayLM-Gemma-3-27B-IT-v2.0-mlx-fp16, is a 27 billion parameter instruction-tuned language model. It is a conversion of the INSAIT-Institute/MamayLM-Gemma-3-27B-IT-v2.0 model into the MLX format, specifically using mlx-lm version 0.31.2. The MLX format is designed for optimized performance on Apple silicon.

Key Characteristics

  • Parameter Count: 27 billion parameters, offering a balance between capability and computational requirements.
  • Instruction-Tuned: Optimized for following instructions and engaging in conversational AI.
  • MLX Conversion: Specifically prepared for efficient inference on Apple silicon, making it suitable for local deployment on compatible hardware.
  • Base Model: Derived from the MamayLM-Gemma-3 series by INSAIT-Institute.

Usage

This model is intended for use with the mlx-lm library, enabling straightforward loading and generation of text. It supports standard prompt formats, including chat templates for conversational interactions.

Good For

  • Developers working with Apple silicon who require an optimized large language model for local inference.
  • Applications requiring a capable instruction-following model for tasks like text generation, summarization, and question answering.
  • Experimentation and development of AI applications on MLX-compatible hardware.