alexgusevski/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-fp16

Hugging Face
TEXT GENERATIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kPublished:Jan 12, 2026Architecture:Transformer Warm

The alexgusevski/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-fp16 is a 12 billion parameter language model, converted to MLX format from DavidAU's original model. It supports a 32768 token context length. This model is designed for general text generation and understanding tasks, leveraging its base architecture for broad applicability. Its primary use case is within MLX-powered applications, offering efficient inference on Apple silicon.

Loading preview...

Overview

This model, alexgusevski/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus-mlx-fp16, is a 12 billion parameter language model. It has been converted to the MLX format from the original DavidAU/Mistral-Nemo-Inst-2407-12B-Thinking-Uncensored-HERETIC-HI-Claude-Opus model, utilizing mlx-lm version 0.29.1. This conversion enables optimized performance on Apple silicon.

Key Capabilities

  • MLX Compatibility: Specifically formatted for use with the MLX framework, ensuring efficient execution on compatible hardware.
  • General Text Generation: Capable of generating human-like text based on provided prompts.
  • Instruction Following: Designed to respond to instructions, making it suitable for various conversational and task-oriented applications.

Good for

  • Developers working with Apple silicon who require an optimized 12B parameter model.
  • Applications requiring general-purpose text generation and understanding.
  • Experimentation and deployment within the MLX ecosystem.

Popular Sampler Settings

Top 3 parameter combinations used by Featherless users for this model. Click a tab to see each config.

temperature
top_p
top_k
frequency_penalty
presence_penalty
repetition_penalty
min_p