Model reference · open weights

gemma-3n-litert-lm

LLMs google Text gen 1 build Open, with conditions 14k dl/mo

gemma-3n-litert-lm is an open-weight language model from Google.

  • Gemma 3n E4B is a multimodal model by Google designed for text generation and efficient execution on low-resource devices.
  • It supports inputs in text, image, video, and audio formats, with a total input context of 32K tokens and output length up to 32K tokens.
  • The model was trained on data in over 140 spoken languages and uses selective parameter activation to operate at an effective size of 4B parameters.
  • It is released under the gemma license.

Summary of the google/gemma-3n-E4B-it-litert-lm model card, 2026-10-01

What it is

Released byGoogle
Released2025-06-06

How it works

How language models work

Your prompttext / messagesTransformerattention over tokensNext-token loopgenerate + streamResponsetext · tool callsA language model reads your tokens and predicts the next one, again and again, streaming the reply back.
© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms