TLDRocket
Sign in

Multimodal Models

102 summarised stories about Multimodal Models, each linking back to the original source. Browse all topics →

+ Follow this topic

Wednesday, 12 March 2025

Welcome Gemma 3: Google's all new multimodal, multilingual, long context open LLM

Hugging Face 1 year ago 30

Google released Gemma 3, a new family of open-weight language models available in four sizes ranging from 1 billion to 27 billion parameters. The 27-billion-parameter instruction-tuned variant achieves an Elo score of 1339 on LMSys Chatbot Arena and outperforms Gemini 1.5-Pro across multiple benchmarks. The larger models now support image and text inputs, process up to 128,000 tokens of context, and handle over 140 languages, making them available immediately on Hugging Face with transformer library integration.

The daily briefing

Every AI story that matters, in your inbox by 8am.

TLDRocket reads all relevant sources, removes duplicate coverage, and summarises the day in two minutes. Follow companies and topics for alerts, or get the briefing in Slack. Free, no spam, unsubscribe anytime.