Title: Florence 2 Base Ft vs Florence 2 Large Ft: Parameters %E2%80%94 LLM EU
Canonical: https://llmeu.com/en/compare/florence-2-base-ft-vs-florence-2-large-ft/
Markdown mirror: https://llmeu.com/en/compare/florence-2-base-ft-vs-florence-2-large-ft.md
Machine-readable: https://llmeu.com/llms.txt (index) - https://llmeu.com/llms-full.txt (full catalogue) - https://llmeu.com/llms-catalogue.json

# Florence 2 Base Ft vs Florence 2 Large Ft

Put two to four models side by side on the fields that decide a deployment: context, price, region, license, languages, hosting, and what is verified.

Where two models differ, this table shows the difference and stops. LLM EU publishes no winner badge without a documented score for that task, and a missing figure stays missing instead of becoming a zero.

## When to use it

### [Florence 2 Base Ft](/en/models/florence-2-base-ft/)

#### Strengths

- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- mit licence, so commercial self-hosting is permitted without a separate agreement
- at 0.2B parameters it fits on a single accelerator

#### Limits

- catalogue only %E2%80%94 LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 0.2B parameters, the weights fit on a single modest accelerator
- a base checkpoint: it answers nothing useful without fine-tuning or a task head
- vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model

#### Tasks

[Vision](/en/tasks/vision/), [Low cost](/en/tasks/cheap/)

### [Florence 2 Large Ft](/en/models/florence-2-large-ft/)

#### Strengths

- open weights are published on Hugging Face and can be downloaded without a vendor agreement
- mit licence, so commercial self-hosting is permitted without a separate agreement
- at 0.8B parameters it fits on a single accelerator

#### Limits

- catalogue only %E2%80%94 LLM EU does not run this model, and nothing on this card implies an LLM EU endpoint
- no evaluation has been run by LLM EU
- the published configuration records no context window, so the card carries none
- at 0.8B parameters, the weights fit on a single modest accelerator
- vision checkpoints are heavier to serve than their parameter count alone suggests, because the image encoder and pre-processing run alongside the language model

#### Tasks

[Vision](/en/tasks/vision/)

**Tasks:** [Vision](/en/tasks/vision/)

## Compare models

- [EmbeddingGemma 300M vs Florence 2 Base Ft](/en/compare/embeddinggemma-300m-vs-florence-2-base-ft/)
- [ERNIE 4.5 0.3B vs Florence 2 Base Ft](/en/compare/ernie-4-5-0-3b-vs-florence-2-base-ft/)
- [Flan T5 Base vs Florence 2 Base Ft](/en/compare/flan-t5-base-vs-florence-2-base-ft/)
- [Flan T5 Small vs Florence 2 Base Ft](/en/compare/flan-t5-small-vs-florence-2-base-ft/)
- [Florence 2 Base Ft vs Gpt Neo 125M](/en/compare/florence-2-base-ft-vs-gpt-neo-125m/)
- [Florence 2 Base Ft vs Granite Docling 258M](/en/compare/florence-2-base-ft-vs-granite-docling-258m/)