mremila/Llama-3.1-8B-coding
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:8kPublished:Mar 19, 2026Architecture:Transformer Cold

mremila/Llama-3.1-8B-coding is an 8 billion parameter causal language model, fine-tuned from meta-llama/Meta-Llama-3.1-8B, with an 8192 token context length. This model is specifically optimized for coding tasks, leveraging its base architecture for enhanced code generation and understanding. It is suitable for developers seeking a specialized model for programming-related applications.

Loading preview...