1.  [](/)
2.  [Models](/models)
3.  MetaCLIP ViT-H/14 (2.5B)

Runs as a custom pluginEmbeddingVerified 2026-11-12

# MetaCLIP ViT-H/14 (2.5B)

facebook/metaclip-h14-fullcc2.5b

MetaCLIP ViT-H/14 (2.5B) is a image and text embedding model (cc-by-nc-4.0, 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/metaclip-h14-fullcc2-5b.json)

No demo for MetaCLIP ViT-H/14 (2.5B) 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 57.5 and Flickr30k 85.0.

Worst at

Non-commercial license; measured 6.5 points under its paper on Flickr30k through Mixpeek, undiagnosed (SOTA bench finding 13).

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

1024

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

986 M

Size on disk

3,945 MB

Preprocessing

Resize and center-crop to 224, 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 MetaCLIP ViT-H/14 (2.5B) best at?

Published COCO 5k recall@1 57.5 and Flickr30k 85.0.

What are the limits of MetaCLIP ViT-H/14 (2.5B)?

Non-commercial license; measured 6.5 points under its paper on Flickr30k through Mixpeek, undiagnosed (SOTA bench finding 13).

Can MetaCLIP ViT-H/14 (2.5B) be used commercially?

No. CC BY-NC 4.0: non-commercial use only.

How does MetaCLIP ViT-H/14 (2.5B) 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 MetaCLIP ViT-H/14 (2.5B) output?

A 1024-dimensional dense vector, compared by cosine similarity.

## Identity

Catalog id

`metaclip-h14-fullcc2-5b`

Family

metaclip

Hub id

`facebook/metaclip-h14-fullcc2.5b`

License

cc-by-nc-4.0

Commercial use

Not allowedCC BY-NC 4.0: non-commercial use only.

Released

2023-10-09

Last verified

Verified 2026-11-12

Paper

[arxiv.org/abs/2309.16671](https://arxiv.org/abs/2309.16671)

Code

[github.com/facebookresearch/MetaCLIP](https://github.com/facebookresearch/MetaCLIP)

## References and formats

*   `hf://facebook/metaclip-h14-fullcc2.5b@ff60fc0029c2f7f7010c9a5b4869163e79903c08`

Format

File

Loads today

safetensors

model.safetensors

Yes

## Related models

*   [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
*   [LAION CLAP HTSAT-tiny (630k-audioset-best)](/models/clap-htsat-tiny)Embedding

## Sources

*   [huggingface.co/facebook/metaclip-h14-fullcc2.5b](https://huggingface.co/facebook/metaclip-h14-fullcc2.5b)
*   [arxiv.org/abs/2309.16671](https://arxiv.org/abs/2309.16671)
*   [github.com/facebookresearch/MetaCLIP](https://github.com/facebookresearch/MetaCLIP)