SlimGroove/normistral-11b-warm-mlx

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

SlimGroove/normistral-11b-warm-mlx is a 12 billion parameter language model, converted by SlimGroove to the MLX format from norallm/normistral-11b-warm. This model is designed for efficient deployment and inference on Apple Silicon, leveraging the MLX framework. It provides a readily available solution for developers seeking to utilize a powerful Mistral-based model within the MLX ecosystem.

Loading preview...

Overview

SlimGroove/normistral-11b-warm-mlx is a 12 billion parameter language model, originally developed by norallm as normistral-11b-warm. This specific version has been converted by SlimGroove into the MLX format using mlx-lm version 0.29.1, making it optimized for Apple Silicon.

Key Capabilities

  • MLX Compatibility: Directly usable with the mlx-lm library for efficient inference on Apple hardware.
  • Mistral-based Architecture: Leverages the underlying architecture of the Mistral family of models, known for strong performance across various tasks.
  • Easy Integration: Provides straightforward Python code examples for loading and generating text, facilitating quick setup for developers.

Good For

  • Developers working with Apple Silicon (Macs with M-series chips) who require a powerful, locally runnable language model.
  • Applications benefiting from on-device inference where MLX's optimizations can provide significant speed advantages.
  • Experimentation and development with a 12 billion parameter model without needing cloud-based GPUs.