HGRN2 3B
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
- 2.9B
- Training data
- 100,000,000,000 tokens
2.9B
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
- 1.7 × 10²¹ FLOP
- How it was established
- Operation counting
6ND = 6* 2.9*10^9*100*10^9 = 1.74e+21
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
What this model is
HGRN2 3B 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.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Training and provenance
Producing it required around 1.7 × 10²¹ FLOP of arithmetic, which is a statement about the training budget rather than about inference.
Around 100,000,000,000 tokens went into training it.
Answers
HGRN2 3B — common questions
How much compute was used to train HGRN2 3B?
Around 1.7 × 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.
What GPU do I need to run HGRN2 3B?
None. HGRN2 3B 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 HGRN2 3B open source?
The licensing for HGRN2 3B was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
How many parameters does HGRN2 3B have?
HGRN2 3B has 2.9B parameters. 2.9B. 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 HGRN2 3B?
HGRN2 3B was published by Shanghai AI Lab,Massachusetts Institute of Technology (MIT),Taptap, based in China, categorised as academia,Academia,Industry.
When was HGRN2 3B released?
HGRN2 3B 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.
What is HGRN2 3B used for?
HGRN2 3B works in Language, and is recorded as handling language modeling/generation, Question answering. A model can carry several of each, so these are the areas it was built for rather than a limit on what it will attempt.
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.