NOMI GPT
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
- NIO
- Organisation type
- Industry
- Country
- China
- Published
- 12 April 2024
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Multimodal, Language, Vision, Speech
- Task
- Object recognition, Audio question answering, System control, Instruction interpretation, Speech recognition (ASR), Language modeling/generation, Question answering, Audio classification, Text classification
- Base model
- TinyBert,wave2vec 2.0 LARGE
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.
- Training data
- tokens
Therefore, the more speech/text data NOMI learns, the higher the accuracy of the "multimode rejection" model judgment. NOMI passed Over 12,000 hours of in-vehicle voice, over 20 million texts "Learning" allows "multi-mode rejection" in the entire field
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Unknown
Sources
Where this record came from and when it was last checked.
- Reference
- NOMI GPT How to Conversate Precisely?
- Last updated
- 28 November 2025
What the numbers mean
About this model
NOMI GPT was published by NIO, in the country recorded as China, during April 2024. It comes out of an organisation categorised as industry.
It works in the domain of Multimodal, Language, Vision, Speech, and is recorded as performing the task of object recognition, Audio question answering, System control, Instruction interpretation, Speech recognition (ASR), Language modeling/generation, Question answering, Audio classification, Text classification.
Rather than being trained from scratch, it is derived from TinyBert,wave2vec 2.0 LARGE. Most models at this scale are adapted from an existing base rather than built from nothing.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Answers
NOMI GPT — common questions
NOMI GPT— is it open source?
The licensing was never recorded in our source data. We treat unstated licensing as closed, because an unrecorded licence is not one to rely on.
NOMI GPT— how many parameters does it have?
No parameter count has been published for it, which is why no memory or speed figure appears on this page.
NOMI GPT— who created it?
It was published by NIO, based in China, an organisation categorised as industry.
NOMI GPT— when was it released?
It 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.
NOMI GPT— what is it used for?
It works in the domain of Multimodal, Language, Vision, Speech, and is recorded as handling the task of object recognition, Audio question answering, System control, Instruction interpretation, Speech recognition (ASR), Language modeling/generation, Question answering, Audio classification, Text classification. 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.
NOMI GPT— 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.
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.