Composer 2.5
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
- Cursor
- Organisation type
- Industry
- Country
- United States of America
- Published
- 18 May 2026
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Language
- Task
- Coding
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
- 1T
- Training data
- tokens
Based on Kimi K2.5; 1.04T total, 32B active parameters
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
- 3.9 × 10²⁵ FLOP
Said by Cursor that 85% of the total compute was performed by their team (from figure following "Composer 2.5 is built on the same open-source checkpoint as Composer 2, Moonshot's Kimi K2.5." here https://cursor.com/blog/composer-2-5) - 5.8e24 / 0.15 = 3.8666666667E25 FLOP
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 B300 (Blackwell Ultra)
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Why it is tracked
- Discretionary
- Record confidence
- Likely
Model available by default in Cursor, which has >1M DAU; reasonable to assume >1M MAU for this model.
Sources
Where this record came from and when it was last checked.
- Reference
- Introducing Composer 2.5
- Last updated
- 4 June 2026
What the numbers mean
About this model
Composer 2.5 was published by Cursor, in the country recorded as United States of America, during May 2026. It comes out of an organisation categorised as industry.
It works in the domain of Language, and is recorded as performing the task of coding.
Its weights were never published, so it can only be reached through its provider. No graphics card changes that.
What went into building it
The training run consumed about 3.9 × 10²⁵ FLOP, on hardware recorded as NVIDIA B300 (Blackwell Ultra). That figure measures what producing the model cost, and has no bearing on how fast it answers.
The reason it appears in this catalogue at all: discretionary.
Answers
Composer 2.5 — common questions
Composer 2.5— when was it released?
It was published in May 2026.
Composer 2.5— what is it used for?
It works in the domain of Language, and is recorded as handling the task of coding. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Composer 2.5— how much compute was used to train it?
Training consumed around 3.9 × 10²⁵ FLOP, on hardware recorded as NVIDIA B300 (Blackwell Ultra). 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.
Composer 2.5— 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.
Composer 2.5— 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.
Composer 2.5— how many parameters does it have?
It has a parameter count of 1T. Based on Kimi K2.5; 1.04T total, 32B active parameters. 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.
Composer 2.5— who created it?
It was published by Cursor, based in United States of America, an organisation categorised as industry.
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.