Florence-2-L (large)
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
- Microsoft
- Organisation type
- Industry
- Country
- United States of America
- Published
- 29 July 2024
- Authors
- Bin Xiao, Haiping Wu, Weijian Xu, Xiyang Dai, Houdong Hu, Yumao Lu, Michael Zeng, Ce Liu, Lu Yuan
What it does
The problem areas the model was built for. A model can carry several of each.
- Domain
- Vision
- Task
- Image captioning, Visual question answering, Image classification, Object detection
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
- 771M
- Training data
- 22,879,290,000 tokens
771 million
We train our models with a mini-batch size of 2048/3072 (base/large) and an image size of 384×384 until reaching 3 billion effective training samples. Similar to [15, 29, 64, 92, 95], we further conduct high-resolution tuning with an image size of 768×768 for 0.5 billion samples for the base model and 0.1 billion samples for the large model. assuming (!) patches 14*14 and avg of 40 text tokens per image: 3*10^9*((384/14)^2+40) + 0.1*10^9*((768/14)^2+40) = 2.6819102e+12 tokens (Likely confide…
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
- 1.2 × 10²² FLOP
- How it was established
- Operation counting
6ND = 6*771000000.00*2681910200000 = 1.2406517e+22
Availability
Whether you can obtain the model and run it on your own hardware, which is what decides if any of the graphics-card figures on this page apply.
- Weights
- Closed — provider access only
- Model access
- Unreleased
- Training code
- Unreleased
How it is classified
Labels the source dataset applies when tracking notable models, and how confident it is in the entry.
- Record confidence
- Likely
Sources
Where this record came from and when it was last checked.
- Reference
- Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
- Last updated
- 11 February 2026
What the numbers mean
Where it came from
Florence-2-L (large) was published by Microsoft, in the country recorded as United States of America, during July 2024. It comes out of an organisation categorised as industry.
It works in the domain of Vision, and is recorded as performing the task of image captioning, Visual question answering, Image classification, Object detection.
Because the weights are not available, none of the hardware figures elsewhere on this site apply to it.
Training and provenance
Training it took a computation budget of roughly 1.2 × 10²² FLOP. That figure measures what producing the model cost, and has no bearing on how fast it answers.
The training set ran to roughly 22,879,290,000 tokens of text.
Answers
Florence-2-L (large) — common questions
Florence-2-L (large)— what is it used for?
It works in the domain of Vision, and is recorded as handling the task of image captioning, Visual question answering, Image classification, Object detection. Models frequently carry more than one of each, and the tags describe purpose rather than capability limits.
Florence-2-L (large)— how much compute was used to train it?
Training consumed around 1.2 × 10²² 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.
Florence-2-L (large)— 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.
Florence-2-L (large)— is it open source?
No. Its weights have not been published, so it exists only as a service controlled by its owner.
Florence-2-L (large)— how many parameters does it have?
It has a parameter count of 771M. 771 million. 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.
Florence-2-L (large)— who created it?
It was published by Microsoft, based in United States of America, an organisation categorised as industry.
Florence-2-L (large)— when was it released?
It was published in July 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.
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.