1.  [](/)
2.  [Models](/models)
3.  DFN2B CLIP ViT-L/14

Runs as a custom pluginEmbeddingVerified 2026-11-12

# DFN2B CLIP ViT-L/14

apple/DFN2B-CLIP-ViT-L-14

DFN2B CLIP ViT-L/14 is a image and text embedding model (apple-amlr, non-commercial). Can run on Mixpeek as an imported Hugging Face model.

Mixpeek does not run it today. It can run as a custom plugin: the weights load without remote code.

[Record as JSON](/models/dfn2b-clip-vit-l-14.json)

No demo for DFN2B CLIP ViT-L/14 yet

A video, image, slideshow or playground goes here once we record one on our own data.

## What it is good and bad at

Best at

Published COCO 5k recall@1 59.6 and Flickr30k 84.7 at ViT-L size.

Worst at

Non-commercial license; ships no preprocessor\_config.json (Mixpeek builds one from open\_clip\_config.json); 77-token text.

Task

Embedding

Input

Image, Text

Output

Vector

Use cases

Visual search

## Templates that use it

No template uses this model yet. [Browse templates](/templates).

## Input and output

### Input

Image

Resolution

224x224

Color

RGB

Normalize

CLIP mean (0.4815, 0.4578, 0.4082), std (0.2686, 0.2613, 0.2758)

Text

Max tokens

77

Prompts

captions as written; CLIP BPE tokenizer (lowercases), 77 tokens

### Output

Vector

Dims

768

Distance

cosine

Type

dense

Note

image and text vectors share one space; L2-normalize before cosine

## How Mixpeek wires it

Extractors

None today

Feature URIs

None today

Vector indexes

None

Retriever stages

feature\_search, mmr

Combines with

*   video frames (VideoFrameExpander) -> image vectors -> feature\_search with a text query
*   detector boxes (RT-DETR, D-FINE) -> crops -> image vectors per object
*   image vectors + E5 text vectors on captions -> feature\_search fusion (dbsf)

## How it runs

Status

Runs as a custom plugin Imported from the Hugging Face Hub as an hf:// extractor and served by the transformers image-text loader, safetensors only, trust\_remote\_code false. GPU recommended at this size.

Serve apps

None

Runtime

transformers CLIPModel + CLIPProcessor

Weights

safetensors, no remote code

Parameters

428 M

Size on disk

1,710 MB

Preprocessing

Resize to 224x224 without a crop (open\_clip resize\_mode squash), CLIP mean/std normalize; tokenize to 77.

Postprocessing

L2-normalize; cosine similarity.

Serving

both, batch 32

Hardware

Runs on CPU (slower without a GPU)

### Scale to zero

Minimum replicas

0

Maximum replicas

1

Idle timeout

600 s

Memory

6 GB

CPUs

2

GPUs

1

Cold start, node warm

Not recorded

Cold start, new node

Not recorded

## Measured cost

Unmeasured

No committed measurement on Mixpeek yet; the SOTA bench measures it.

## Our evaluations

Unmeasured

We have not evaluated this model on our own data yet. Publisher results are in the sources below.

## Questions

What is DFN2B CLIP ViT-L/14 best at?

Published COCO 5k recall@1 59.6 and Flickr30k 84.7 at ViT-L size.

What are the limits of DFN2B CLIP ViT-L/14?

Non-commercial license; ships no preprocessor\_config.json (Mixpeek builds one from open\_clip\_config.json); 77-token text.

Can DFN2B CLIP ViT-L/14 be used commercially?

No. Apple AMLR (sample code) license: research use; the weights are not licensed for commercial products.

How does DFN2B CLIP ViT-L/14 run on Mixpeek?

Imported from the Hugging Face Hub as an hf:// extractor and served by the transformers image-text loader, safetensors only, trust\_remote\_code false. GPU recommended at this size.

What does DFN2B CLIP ViT-L/14 output?

A 768-dimensional dense vector, compared by cosine similarity.

## Identity

Catalog id

`dfn2b-clip-vit-l-14`

Family

dfn

Hub id

`apple/DFN2B-CLIP-ViT-L-14`

License

apple-amlr

Commercial use

Not allowedApple AMLR (sample code) license: research use; the weights are not licensed for commercial products.

Released

2023-10-30

Last verified

Verified 2026-11-12

Paper

[arxiv.org/abs/2309.17425](https://arxiv.org/abs/2309.17425)

Code

[github.com/apple/ml-mobileclip](https://github.com/apple/ml-mobileclip)

## References and formats

*   `hf://apple/DFN2B-CLIP-ViT-L-14@d431cb9b550f020c753196f5871c1b7c0dfae5e8`

Format

File

Loads today

safetensors

2 files, model.safetensors (transformers) and open\_clip\_pytorch\_model.safetensors (open\_clip, not read)

Yes

## Related models

*   [DFN5B CLIP ViT-H/14](/models/dfn5b-clip-vit-h-14)Embedding
*   [Multilingual E5 Large Instruct](/models/multilingual-e5-large-instruct)Embedding
*   [Gemini Embedding 2](/models/gemini-embedding-2)Embedding
*   [all-MiniLM-L6-v2](/models/all-minilm-l6-v2)Embedding
*   [Vertex AI multimodalembedding@001](/models/multimodalembedding)Embedding
*   [SigLIP Base patch16 224](/models/siglip-base-patch16-224)Embedding

## Sources

*   [huggingface.co/apple/DFN2B-CLIP-ViT-L-14](https://huggingface.co/apple/DFN2B-CLIP-ViT-L-14)
*   [arxiv.org/abs/2309.17425](https://arxiv.org/abs/2309.17425)
*   [github.com/apple/ml-mobileclip](https://github.com/apple/ml-mobileclip)