Hunyuan-TurboS

Training compute

5.4×10²⁴ FLOP

Parameters

560B

Published

Mar 11, 2025

Hunyuan-TurboS is an AI model developed by Tencent (China), first published in March 2025. It works in the language domain, on tasks such as language modeling/generation, quantitative reasoning, question answering and 2 more.

Training it took an estimated 5.4×10²⁴ FLOP of compute. The model has 560,000,000,000 parameters. It was trained on roughly 16T datapoints.

Access: API access. Its weights are not openly released. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Tencent
Country of organization: China
Domain: Language
Task: Language modeling/generation, Quantitative reasoning, Question answering, Code generation, Text summarization
Training compute: 5.4×10²⁴ FLOP
Parameters: 560,000,000,000
Dataset size: 16T
Model accessibility: API access
Open weights: No
Epoch confidence: Confident