Kimi-VL
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
- Moonshot
- Organisation type
- Industry
- Country
- China
- Published
- 23 June 2025
- Authors
- Kimi Team
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Multimodal, Vision, Language
- Task
- Language modeling/generation, Object recognition, Mathematical reasoning
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
- 16B
- Training data
- tokens
Structurally, Kimi-VL consists of our Moonlight (J. Liu et al. 2025a) MoE language model with only 2.8B activated (16B total) parameters, paired with a 400M native-resolution MoonViT vision encoder.
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
- KIMI-VL TECHNICAL REPORT
- Last updated
- 28 November 2025
What the numbers mean
Where it came from
Kimi-VL was published by Moonshot, in China, in June 2025. The organisation is categorised as industry.
It works in Multimodal, Vision, Language, and is recorded as doing language modeling/generation, Object recognition, Mathematical reasoning.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
Answers
Kimi-VL — common questions
Who created Kimi-VL?
Kimi-VL was published by Moonshot, based in China, categorised as industry.
When was Kimi-VL released?
Kimi-VL was published in June 2025.
What is Kimi-VL used for?
Kimi-VL works in Multimodal, Vision, Language, and is recorded as handling language modeling/generation, Object recognition, Mathematical reasoning. These are the areas it was designed around; they describe intent rather than a hard boundary.
What GPU do I need to run Kimi-VL?
None. Kimi-VL 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 Kimi-VL open source?
The licensing for Kimi-VL 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 Kimi-VL have?
Kimi-VL has 16B parameters. Structurally, Kimi-VL consists of our Moonlight (J. Liu et al. 2025a) MoE language model with only 2.8B activated (16B total) parameters, paired with a 400M native-resolution MoonViT vision encoder. 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.
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.