
Rin-mobile is a compact model destined to run agentic work directly on a phone or a laptop, with no server and no cloud. It was trained on about 895,000 tokens to give it one steady voice, named Rin, that is clear and composed.
What it does
- Text to text. Chat, coding, technical help, and long horizon agentic tasks that hold together across many steps.
- Image to text. Look at a picture and describe or reason about it.
- Speech to text. Take an audio clip and transcribe or answer from it.
It also does private step by step reasoning and tool calls.
Run it on device
Quantized for phone class hardware (about 4.4 GB):
ollama pull Loke-60000/rin-mobile-preview
ollama run Loke-60000/rin-mobile-preview "what is in this photo? image.png"
ollama run Loke-60000/rin-mobile-preview "transcribe this clip.wav"
Run it with transformers
from transformers import AutoProcessor, AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("Loke-60000/rin-mobile-preview")
processor = AutoProcessor.from_pretrained("Loke-60000/rin-mobile-preview")