HGRN2 1B

Closed weights Shanghai AI Lab,Massachusetts Institute of Technology (MIT),Taptap 1B parameters April 2024

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
Shanghai AI Lab,Massachusetts Institute of Technology (MIT),Taptap
Organisation type
Academia,Academia,Industry
Country
China, United States of America, Spain
Published
11 April 2024
Authors
Zhen Qin, Songlin Yang, Weixuan Sun, Xuyang Shen, Dong Li, Weigao Sun, Yiran Zhong

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

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
1B

1B

Training data
100,000,000,000 tokens

100B Table 6

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
6 × 10²¹ FLOP

6ND = 6*10^9 * 100*10^9 = 6*10^21

How it was established
Operation counting

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
HGRN2: Gated Linear RNNs with State Expansion
Last updated
28 November 2025

What the numbers mean

Background

HGRN2 1B was published by Shanghai AI Lab,Massachusetts Institute of Technology (MIT),Taptap, in China, in April 2024. It comes out of academia,Academia,Industry.

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

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

Training and provenance

The training run consumed about 6 × 10²¹ FLOP. That figure describes the cost of creating it and has no bearing on how quickly it generates text.

The training set ran to roughly 100,000,000,000 tokens.

Answers

HGRN2 1B — common questions

01

What GPU do I need to run HGRN2 1B?

None. HGRN2 1B 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.

02

Is HGRN2 1B open source?

The licensing for HGRN2 1B was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.

03

How many parameters does HGRN2 1B have?

HGRN2 1B has 1B parameters. 1B. 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.

04

Who created HGRN2 1B?

HGRN2 1B was published by Shanghai AI Lab,Massachusetts Institute of Technology (MIT),Taptap, based in China, categorised as academia,Academia,Industry.

05

When was HGRN2 1B released?

HGRN2 1B was published in April 2024. Capability per parameter has improved considerably since, so a newer model of the same size is often the better use of the same hardware.

06

What is HGRN2 1B used for?

HGRN2 1B works in Language, and is recorded as handling language modeling/generation, Question answering. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.

07

How much compute was used to train HGRN2 1B?

Around 6 × 10²¹ 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.

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.