HNGlance

Top Best New Show

Gemma 3: Google's new multimodal models

https://ai.google.dev/Gemma/docs/core

by danielhanchen • 1 year ago

4 2 1 year ago

AI

Related Stories

Loading related stories...

Comments

2

danielhanchen• 1 year ago

Google released their new Gemma 3 multimodal (text + image) models. Gemma 3 comes in 1B, 4B, 12B, and 27B sizes and the 27B model matches Gemini-1.5-Pro on many benchmarks. It introduces vision understanding, has a 128K context window, and multilingual support in 140+ languages.

Interestingly the model's architecture is very different from Llama, Gemma and PaliGemma's.

sMarsIntruder• 1 year ago

I get 404: right links seems to be https://ai.google.dev/gemma/docs/core

Source preview

ai.google.dev

HNGlance

© 2024-2026 HN Glance. Story content belongs to its original sources.

Privacy
Terms