LoongRL 7B

Closed weights Microsoft Research Asia,Shanghai Jiao Tong University,Carnegie Mellon University (CMU) 7B parameters October 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,Shanghai Jiao Tong University,Carnegie Mellon University (CMU)
Organisation type
Industry,Academia,Academia
Country
China, United States of America
Published
27 October 2025
Authors
Siyuan Wang, Gaokai Zhang, Li Lyna Zhang, Ning Shang, Fan Yang, Dongyao Chen, 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, Question answering, Quantitative reasoning
Base model
Qwen2.5 Instruct (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

7B

Training data
tokens

"Batch sizes are set to 512 for 7B model" "a maximum output length of 4,096 tokens and longcontext inputs of ∼ 16K" "42 steps in warm-up, 168 in Stage I and 118 in Stage II" "After Stage I, we generate eight rollouts per example using the best checkpoint"

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 A100
Chips used
16
Power draw
12.5 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 (non-commercial)

"We have made extensive efforts to ensure the reproducibility of our work. Details of the GRPO algorithm and hyperparameters are provided in Section 3.2.1 and Section 4.1. We provide our training prompt template in Appendix A.2. The datasets used in our experiments are described in Table 1. To further facilitate reproducibility, the supplementary materials include (i) our RL training code, (ii) the code for synthesizing KeyChain data, and (iii) several representative samples of the synthesized K…

How it is classified

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

Record confidence
Confident

Sources

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

Reference
LoongRL: Reinforcement Learning for Advanced Reasoning over Long Contexts
Last updated
28 November 2025

What the numbers mean

Background

LoongRL 7B was published by Microsoft Research Asia,Shanghai Jiao Tong University,Carnegie Mellon University (CMU), in China, in October 2025. industry,Academia,Academia is the category the publisher falls under.

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

It is derived from Qwen2.5 Instruct (7B) 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

LoongRL 7B — common questions

01

Is LoongRL 7B open source?

No. LoongRL 7B has not had its weights published, so it exists only as a service controlled by its owner.

02

How many parameters does LoongRL 7B have?

LoongRL 7B has 7B parameters. 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.

03

Who created LoongRL 7B?

LoongRL 7B was published by Microsoft Research Asia,Shanghai Jiao Tong University,Carnegie Mellon University (CMU), based in China, categorised as industry,Academia,Academia.

04

When was LoongRL 7B released?

LoongRL 7B was published in October 2025.

05

What is LoongRL 7B used for?

LoongRL 7B works in Language, and is recorded as handling language modeling/generation, Question answering, Quantitative reasoning. These are the areas it was designed around; they describe intent rather than a hard boundary.

06

What GPU do I need to run LoongRL 7B?

None. LoongRL 7B 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.

Source

Original publication

Record last updated 28 November 2025

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.