Open-Weight Model Families · 2025
Gemma 3 Technical Report
Adds vision and 128K-token context to Google's lightweight open models (1-27B) using a local/global attention ratio to curb KV-cache growth; open-weight under the custom Gemma license.
Editorial record
Plain-language summary
Adds vision and 128K-token context to Google's lightweight open models (1-27B) using a local/global attention ratio to curb KV-cache growth; open-weight under the custom Gemma license.
Knowledge graph
Relationships
Descendants
Depends onEvidence: Strongly supported
Attention Is All You Need
Builds on the open weight family lineage in the archive
freshness sweep 2026
Source record
Provenance
- Record ID
- P-627
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
- https://arxiv.org/abs/2503.19786
- arXiv:2503.19786
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.