Skip to content
AI Model Radar

DiarizationLM Gemma 4 E4B v1

google/DiarizationLM-Gemma-4-E4B-v1
Open Source · chat · open-weights
Unavailable Alert me on changes
Not currently available. This model's weights can't currently be fetched from Hugging Face, so it isn't usable right now. We re-check every few minutes and will alert subscribers the moment it returns.
Context
131.1K
Max output
—
Weights
Unavailable
API $/1M
—
Modalities
text · image
Released
04 Oct 2026
License: apache-2.0 · google/DiarizationLM-Gemma-4-E4B-v1
Download image Share on X Share on LinkedIn
AI summary
● machine-written

Google releases DiarizationLM Gemma 4 E4B v1 open-weight model

DiarizationLM Gemma 4 E4B v1 is an open-weight speaker diarization model built on the Gemma 4 E4B foundation with 4 billion dense parameters, fine-tuned using Locality-Preserving Oracle Supervision. Released under Apache 2.0 license, it supports a 131.1K token context window and multimodal input (text and image).

What's new
  • Built on Gemma 4 E4B foundation with 4 billion dense parameters
  • Fine-tuned using Locality-Preserving Oracle Supervision
  • Released under Apache 2.0 open-source license
  • 131.1K token context window with multimodal capabilities
  • Available as open-weight model for self-hosting
Best for
Speaker diarization tasksOn-device deploymentOpen-source model researchMultimodal text and image processing
Sources

Source: https://huggingface.co/google/DiarizationLM-Gemma-4-E4B-v1