legmlai/legml-v1.0-8b-instruct
TEXT GENERATIONConcurrency Cost:1Model Size:8BQuant:FP8Ctx Length:32kLicense:apache-2.0Architecture:Transformer0.0K Open Weights Cold

The legmlai/legml-v1.0-8b-instruct model is an 8 billion parameter instruction-tuned causal language model, based on Qwen-3, developed by legml.ai. It is specifically fine-tuned on Open-Hermes-FR, a corpus of nearly 800,000 instruction/response pairs exclusively in French. This model is optimized for high-quality, rigorous French language generation, making it ideal for francophone dialogue, reasoning, and question-answering tasks.

Loading preview...