alexgusevski/Mistral-Nemo-Instruct-2407-heretic-noslop-mlx-fp16
TEXT GENERATIONConcurrency Cost:1Model Size:12BQuant:FP8Ctx Length:32kPublished:Jan 12, 2026License:apache-2.0Architecture:Transformer Open Weights Cold

The alexgusevski/Mistral-Nemo-Instruct-2407-heretic-noslop-mlx-fp16 is a 12 billion parameter instruction-tuned language model, converted to the MLX format by alexgusevski from the original p-e-w/Mistral-Nemo-Instruct-2407-heretic-noslop model. This model supports a 32768 token context length and is designed for efficient deployment and inference on Apple silicon via the MLX framework. It is suitable for general instruction-following tasks, leveraging the Mistral architecture for robust performance.

Loading preview...