Modelle: Übersicht und Einsatz

30 April 2026 Von admin Aus

Name,Size,Context,Input

translategemma

A new collection of open translation models built on Gemma 3, helping people communicate across 55 languages.

Models

Name	Size	Context	Input
translategemma:latest	3.3GB	128K	Text, Image
translategemma:4b (latest)	3.3GB	128K	Text, Image
translategemma:12b	8.1GB	128K	Text, Image
translategemma:27b	17GB	128K	Text, Image

ollama run translategemma

from ollama import chat

response = chat(
    model='translategemma',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

glm-ocr

GLM-OCR is a multimodal OCR model for complex document understanding, built on the GLM-V encoder–decoder architecture.

Links: github.com

ollama run glm-ocr

# Text recognition
ollama run glm-ocr Text Recognition: ./image.png

# Table recognition
ollama run glm-ocr Table Recognition: ./image.png

# Figure recognition
ollama run glm-ocr Figure Recognition: ./image.png

KategorieUncategorised