Skip to content
Local AI Wizard
Your machine
Theme

siglip-base-patch16-224

Google · google/siglip-base-patch16-224

Weights license: Apache 2.0 · code and components may use other terms

Hub downloads · 30 days1.1MPopularity, not quality · read 2026-10-25
Memory needed~3 GB16-bit estimate · not measured
Parameters0.2 BHub safetensors total
Repository updated2024-09-26A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

The publisher's card states no benchmark result for this checkpoint (read 2026-10-25). not published on the card · read 2026-10-25

Runs on

Fast memory holds it 119

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 119

Hardware profiles grouped by a labelled 16-bit planning estimate from the Hugging Face parameter count (2 bytes per parameter, 20% allowance, 2 GB reserve): classic vision encoders are not usually quantized. Image size and batch change the real requirement. Not a measured fit.

Consider it for

siglip-base-patch16-224 by Google (the publisher states no release date): an image-text encoder for zero-shot classification and retrieval, with 200M parameters on the Hugging Face count and the Apache 2.0 license.

Check first

License: commercial use allowed. The 16-bit estimate is about 3 GB with reserve; image size and batch change the real figure.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Transformers · model card · How to use
from PIL import Image
import requests
from transformers import AutoProcessor, AutoModel
import torch

model = AutoModel.from_pretrained("google/siglip-base-patch16-224")
processor = AutoProcessor.from_pretrained("google/siglip-base-patch16-224")

url = "http://images.cocodataset.org/val2017/000000039769.jpg"
image = Image.open(requests.get(url, stream=True).raw)

texts = ["a photo of 2 cats", "a photo of 2 dogs"]
inputs = processor(text=texts, images=image, padding="max_length", return_tensors="pt")

with torch.no_grad():
    outputs = model(**inputs)

logits_per_image = outputs.logits_per_image
probs = torch.sigmoid(logits_per_image) # these are the probabilities
print(f"{probs[0][0]:.1%} that image 0 is '{texts[0]}'")
Transformers · model card · How to use
from transformers import pipeline
from PIL import Image
import requests

# load pipe
image_classifier = pipeline(task="zero-shot-image-classification", model="google/siglip-base-patch16-224")

# load image
url = 'http://images.cocodataset.org/val2017/000000039769.jpg'
image = Image.open(requests.get(url, stream=True).raw)

# inference
outputs = image_classifier(image, candidate_labels=["2 cats", "a plane", "a remote"])
outputs = [{"score": round(output["score"], 4), "label": output["label"] } for output in outputs]
print(outputs)

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Task
zero-shot-image-classification
Architecture
SiglipModel
Library in source
transformers
Weight license
Apache 2.0google/siglip-base-patch16-224 model card (Hugging Face) · read 2026-10-18source
Commercial use
Allowed Apache License 2.0 text (SPDX) · read 2026-10-18license text
Released
Not published by the publisher. Card read; the publisher's google-research/big_vision README (every revision) links the SigLIP models without a date, the SigLIP paper (arXiv 2303.15343, v1 2023-03-27) does not announce these checkpoints, and the Hugging Face blog index has no SigLIP post. No date is inferred from the paper, commits or the repository.Checked 2026-10-18.source checked
Every stored field11 fields
Revision checked
7fd15f0689c79d79e38b1c2e2e2370a7bf2761ed
Architecture
SiglipModel
Library
transformers
Hub task tag
zero-shot-image-classification
Formats
transformers, pytorch, safetensors
Access
Open download
Publisher kind
Official
Repository created
2023-09-30creation is not the model's release
Repository updated
2024-09-26a commit is not a release date
Hub downloads (30 days) · likes
1,084,847 · 103this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-18. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.