SlimGroove/normistral-11b-translate-mlx

TEXT GENERATIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kPublished:Apr 21, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

SlimGroove/normistral-11b-translate-mlx is a 12 billion parameter language model, converted to the MLX format from norallm/normistral-11b-translate. This model is specifically designed for efficient deployment and inference on Apple silicon, leveraging the MLX framework. It provides a performant solution for translation tasks and general language generation on MLX-compatible hardware. Its primary utility lies in enabling local, optimized execution of a powerful language model.

Loading preview...

Model Overview

SlimGroove/normistral-11b-translate-mlx is a 12 billion parameter language model, derived from the norallm/normistral-11b-translate model. This version has been specifically converted to the MLX format using mlx-lm version 0.29.1, making it optimized for efficient inference on Apple silicon.

Key Capabilities

  • MLX Optimization: Designed for high-performance execution on Apple's MLX framework, ensuring efficient local inference.
  • Translation Focus: Based on a model (normistral-11b-translate) that implies a specialization in translation tasks.
  • Large Parameter Count: With 12 billion parameters, it offers robust language understanding and generation capabilities.
  • Context Length: Supports a substantial context length of 32768 tokens, allowing for processing longer inputs.

Good For

  • Developers working with Apple silicon (e.g., M1, M2, M3 chips) who require a powerful language model for local execution.
  • Applications involving translation where efficient on-device processing is crucial.
  • Experimentation and development of MLX-based language model applications.
  • General text generation and understanding tasks on MLX-compatible hardware.