Llama3.1-Typhoon2-8B-Instruct is a Thai-English instruction-tuned model with 8 billion parameters, built on Llama 3.1. It significantly improves over its base model in Thai reasoning, instruction-following, and function-calling tasks, while maintaining competitive English performance. The model is optimized for bilingual interaction and performs well on Thai-English code-switching, MT-Bench, IFEval, and tool-use benchmarks.
Despite its smaller size, it demonstrates strong generalization across math, coding, and multilingual benchmarks, outperforming comparable 8B models across most Thai-specific tasks. Full benchmark results and methodology are available in the technical report.(opens in new tab)
Modalities
Context
8K
Released
Mar 28, 2025
Knowledge Cutoff
Dec 2023
Token volume and request traffic to this model over time.