rStar-Math (Qwen2.5-Math-7B base)
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
- Qwen2.5-Math-7B-Base
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
- Epochs
- 2
- Batch size
- 128
~1.35M trajectories with 4096 sequence length: 5530M
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
What this model is
rStar-Math (Qwen2.5-Math-7B base) was published by Microsoft Research Asia,Peking University,Tsinghua University, in China, in August 2025. It comes out of industry,Academia,Academia.
It works in Language, and is recorded as doing language modeling/generation, Mathematical reasoning.
It is derived from Qwen2.5-Math-7B-Base rather than trained from scratch, which is the usual way a specialised model is produced.
This is a closed model: the trained values stayed with whoever produced them, and there is no local version to run.
Answers
rStar-Math (Qwen2.5-Math-7B base) — common questions
When was rStar-Math (Qwen2.5-Math-7B base) released?
rStar-Math (Qwen2.5-Math-7B base) was published in August 2025.
What is rStar-Math (Qwen2.5-Math-7B base) used for?
rStar-Math (Qwen2.5-Math-7B base) works in Language, and is recorded as handling language modeling/generation, Mathematical reasoning. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
What GPU do I need to run rStar-Math (Qwen2.5-Math-7B base)?
None. rStar-Math (Qwen2.5-Math-7B base) 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.
Is rStar-Math (Qwen2.5-Math-7B base) open source?
No. rStar-Math (Qwen2.5-Math-7B base) has not had its weights published, so it exists only as a service controlled by its owner.
How many parameters does rStar-Math (Qwen2.5-Math-7B base) have?
rStar-Math (Qwen2.5-Math-7B base) has 7B 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.
Who created rStar-Math (Qwen2.5-Math-7B base)?
rStar-Math (Qwen2.5-Math-7B base) was published by Microsoft Research Asia,Peking University,Tsinghua University, based in China, categorised as industry,Academia,Academia.
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.