justindal/llama3.1-8b-instruct-mlx
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kPublished:Mar 19, 2026License:llama3.1Architecture:Transformer Cold

The justindal/llama3.1-8b-instruct-mlx is an 8 billion parameter instruction-tuned language model, converted for use with Apple's MLX framework. Based on Meta's Llama 3.1 architecture, it offers a 32768-token context window. This model is specifically optimized for efficient inference on Apple Silicon, making it suitable for local, high-performance AI applications.

Loading preview...