rStar-Math (Qwen2-Math-7B base)

Closed weights Microsoft Research Asia,Peking University,Tsinghua University 7B parameters August 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
Microsoft Research Asia,Peking University,Tsinghua University
Organisation type
Industry,Academia,Academia
Country
China
Published
1 August 2025
Authors
Xinyu Guan, Li Lyna Zhang, Yifei Liu, Ning Shang, Youran Sun, Yi Zhu, Fan Yang, Mao Yang

What it does

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

Domain
Language
Task
Language modeling/generation, Mathematical reasoning
Base model
Qwen2-Math-7B

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
7B
Training data
tokens

~1.35M trajectories with 4096 sequence length: 5530M

Epochs
2
Batch size
128

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.

How it was established
Operation counting
Fine-tuning compute
2.3 × 10²⁰ FLOP

5530000000 * 7000000000 * 6 = 2.323e20

The training run

What it physically took to train: which chips, how many, for how long, and what that drew from the wall.

Training hardware
NVIDIA H100 SXM5 80GB
Chips used
80
Power draw
109.5 kW

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
Unreleased
Training code
Open source

MIT license https://github.com/microsoft/rStar

How it is classified

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

Record confidence
Confident
Citations
308

Sources

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

Reference
rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking
Last updated
25 May 2026

What the numbers mean

Where it came from

rStar-Math (Qwen2-Math-7B base) was published by Microsoft Research Asia,Peking University,Tsinghua University, in the country recorded as China, during August 2025. The category the publisher falls under is industry,Academia,Academia.

It works in the domain of Language, and is recorded as performing the task of language modeling/generation, Mathematical reasoning.

It builds on Qwen2-Math-7B. That is why it shares the base model's general shape and size.

Its weights were never published, so it can only be reached through its provider. No graphics card changes that.

Answers

rStar-Math (Qwen2-Math-7B base) — common questions

01

rStar-Math (Qwen2-Math-7B base)— what is it used for?

It works in the domain of Language, and is recorded as handling the task of language modeling/generation, Mathematical reasoning. These are the areas it was designed around; they describe intent rather than a hard boundary.

02

rStar-Math (Qwen2-Math-7B base)— what GPU do I need to run it?

None. This 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

rStar-Math (Qwen2-Math-7B base)— is it open source?

No. Its weights have not been published, so it exists only as a service controlled by its owner.

04

rStar-Math (Qwen2-Math-7B base)— how many parameters does it have?

It has a parameter count of 7B. 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

rStar-Math (Qwen2-Math-7B base)— who created it?

It was published by Microsoft Research Asia,Peking University,Tsinghua University, based in China, an organisation categorised as industry,Academia,Academia.

06

rStar-Math (Qwen2-Math-7B base)— when was it released?

It was published in August 2025.

Source

Original publication

Record last updated 25 May 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.