Hunyuan-TurboS

Closed weights Tencent 560B parameters March 2025

No estimate

No hardware requirements for this model

The weights for this model have not been published, so it cannot be downloaded or run on your own hardware at any size. It is reachable only through its provider, and no graphics card changes that.

On record

Full specification

Everything on record for this model. Most of it describes how it was trained rather than how it runs — useful context for judging how much work went into it, and how it compares with models built at a different scale.

Origin

Who built this model, where, and when it was published.

Organisation
Tencent
Organisation type
Industry
Country
China
Published
11 March 2025
Authors
Tencent Hunyuan Team: Ao Liu, Botong Zhou, Can Xu, Chayse Zhou, ChenChen Zhang, Chengcheng Xu, Chenhao Wang, Decheng Wu, Dengpeng Wu, Dian Jiao, Dong Du, Dong Wang, Feng Zhang, Fengzong Lian, Guanghui Xu, Guanwei Zhang, Hai Wang, Haipeng Luo, Han Hu, Huilin Xu, Jiajia Wu, Jianchen Zhu, Jianfeng Yan, Jiaqi Zhu, Jihong Zhang, Jinbao Xue, Jun Xia, Junqiang Zheng, Kai Liu, Kai Zhang, Kai Zheng, Kejiao…

What it does

The problem areas the model was built for. A model can carry several of each.

Domain
Language
Task
Language modeling/generation, Quantitative reasoning, Question answering, Code generation, Text summarization
Approach
Supervised fine-tuning (SFT),Reinforcement learning

Size

How large the model is and how much data it was trained on. Parameters are the figure that decides whether it fits on a given graphics card.

Parameters
560B

the model scales to 56B activated parameters and 560B total parameters

Training data
16,000,000,000,000 tokens

pre-trained on 16T high-quality tokens

Training compute

The arithmetic performed to train the model, measured in floating-point operations. It is a measure of what the training run cost, not of how fast the finished model answers you.

Training compute
5.4 × 10²⁴ FLOP

using C = 6*ND, 6* 56 billion parameters * 16 trillion tokens = ~5.4e24 FLOP

Availability

Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.

Weights
Closed — provider access only
Model access
API access
Training code
Unreleased

API via Tencent Cloud

How it is classified

Labels the source dataset applies when tracking notable models, and how confident it is in the entry.

Likely above 10²³ FLOP
Yes
Why it is tracked
SOTA improvement

Based on the photos published by Tencent on X, it achieved top performance on several benchmarks - MMLU, C-Eval, MATH. (https://x.com/TencentHunyuan/status/1899105803073958010/photo/1)

Record confidence
Confident

Sources

Where this record came from and when it was last checked.

Reference
Tencent HunYuan Turbo S: The fastest reasoning LLM At par with DeepSeek, Claude 3.5 and GPT-4o
Last updated
11 February 2026

What the numbers mean

About this model

Hunyuan-TurboS was published by Tencent, in China, in March 2025. The organisation is categorised as industry.

It works in Language, and is recorded as doing language modeling/generation, Quantitative reasoning, Question answering, Code generation, Text summarization.

Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.

Training and provenance

Training it took roughly 5.4 × 10²⁴ FLOP of computation — a measure of what producing the model cost, not of how fast it answers.

Around 16,000,000,000,000 tokens went into training it.

It is tracked in the underlying dataset for one reason in particular: sOTA improvement.

Answers

Hunyuan-TurboS — common questions

01

How much compute was used to train Hunyuan-TurboS?

Around 5.4 × 10²⁴ FLOP. That measures what producing the model cost and says nothing about how quickly it answers once trained — inference speed comes from memory bandwidth, not from the training budget.

02

What GPU do I need to run Hunyuan-TurboS?

None. Hunyuan-TurboS is a closed model — its weights were never published, so it cannot be downloaded or run on your own hardware at any price. It is reachable only through its provider.

03

Is Hunyuan-TurboS open source?

No. Hunyuan-TurboS has not had its weights published, so it exists only as a service controlled by its owner.

04

How many parameters does Hunyuan-TurboS have?

Hunyuan-TurboS has 560B parameters. the model scales to 56B activated parameters and 560B total parameters. That figure is the total, and it is what decides how much memory the model needs — roughly half a gigabyte per billion at the compression most people use.

05

Who created Hunyuan-TurboS?

Hunyuan-TurboS was published by Tencent, based in China, categorised as industry.

06

When was Hunyuan-TurboS released?

Hunyuan-TurboS was published in March 2025.

07

What is Hunyuan-TurboS used for?

Hunyuan-TurboS works in Language, and is recorded as handling language modeling/generation, Quantitative reasoning, Question answering, Code generation, Text summarization. These are the areas it was designed around; they describe intent rather than a hard boundary.

Source

Original publication

Record last updated 11 February 2026

The other direction

Looking at it from the other side?

This page starts from the model. If you already own a card and want to know everything it will run, start from the hardware instead.