Decision support
MobileCLIP vs Text Embedding 3 Small
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
MobileCLIP
Apple
Benchmark results
No benchmark results have been matched to these models yet.
Model specifications
Release date
March 6, 2024
January 25, 2024
Context window
—
8K
Native context
—
—
Max output tokens
—
7,372
Knowledge cutoff
—
—
Open weights
Open weights
Closed
Parameter count
—
—
API pricing · USD per 1M tokens
Input
—
$0.02
Output
—
$0.00
Cached input
—
—
Cache write
—
—
Capabilities and modalities
Input modalities
text, image
text
Output modalities
embeddings
embeddings
Tool calling
—
—
Reasoning option
—
—
Supported options
—
—
Capabilities
—
—
Architecture and availability
Architecture
—
—
Model families
—
—
Tokenizer
—
Other
Instruction format
—
—
License
apple-amlr
—
Providers
0
2
Provider endpoints
0
4
Ollama variants
0
0
Metadata source
curated
ai-research
A dash means the field is not reported. Provider-specific performance and pricing may differ.