Decision support
AFM 3 Core Advanced vs MiMo-V2.5-TTS-VoiceClone
Compare canonical objects directly. The useful dimensions change with the object type, so model and hardware comparisons stay separate.
AFM 3 Core Advanced
Apple
Benchmark results
No benchmark results have been matched to these models yet.
Model specifications
Release date
June 8, 2026
April 22, 2026
Context window
—
8K
Native context
—
—
Max output tokens
—
8,192
Knowledge cutoff
—
—
Open weights
Closed
Closed
Parameter count
20B
—
API pricing · USD per 1M tokens
Input
—
—
Output
—
—
Cached input
—
—
Cache write
—
—
Capabilities and modalities
Input modalities
text, image, audio
text
Output modalities
text, audio
audio
Tool calling
—
—
Reasoning option
—
—
Supported options
—
—
Capabilities
—
—
Architecture and availability
Architecture
—
—
Model families
—
—
Tokenizer
—
—
Instruction format
—
—
License
proprietary
—
Providers
0
0
Provider endpoints
0
0
Ollama variants
0
0
Metadata source
curated
models.dev
A dash means the field is not reported. Provider-specific performance and pricing may differ.