Vit Base Patch 16 224 In21k
Google's Vision Transformer (ViT) base model, pre-trained on ImageNet-21k, is genuinely best at learning inner representations of images that can be used to extract features for downstream tasks such as image classification. A notable technical trait of this model is its use of a transformer encoder architecture, where images are presented as a sequence of fixed-size patches with absolute position embeddings.
Input
Output
Context
-
Max Output
-
Parameters
86.4M
Technical Specifications
Input Modalities
Output Modalities
Capabilities
Loading capabilities…
Estimated GPU requirements for Vit Base Patch 16 224 In21k
Estimates based on INT8 quantization at up to 32K context. A count above one assumes tensor parallelism across the cards. Actual requirements vary by framework and configuration.
More models by Google
The creator's other models in the catalog, with their context, size and license where published.
Compare it, or keep browsing
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Frequently asked questions about Vit Base Patch 16 224 In21k
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
Google has not published a context window for Vit Base Patch 16 224 In21k, so the catalog shows it as not available rather than estimating one.
Yes. Vit Base Patch 16 224 In21k is an open-weight model released under the Apache 2.0 license, so the weights can be downloaded and self-hosted within that license's terms.
Vit Base Patch 16 224 In21k accepts Image and produces Embedding. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
No published benchmark result for Vit Base Patch 16 224 In21k is in the catalog yet, so the model is shown as unmeasured. It is not ranked or estimated; the router treats it as unknown for every task until a suite measures it.
Not on the managed pool today; Vit Base Patch 16 224 In21k is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
About 0.5 GB at INT8 for the weights and a default context, from the catalog's 86.4M parameter count; FP16 needs roughly twice that, and long contexts or many concurrent requests add KV cache on top. The GPU section on this page lists cards that hold it, and the capacity planner sizes it for your context length and traffic.
Fields collected from public registries, host APIs and benchmark publishers, each tagged with its source.
Last updated: Aug 28, 2026
Put intelligence in the middle.
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.