v0.40.0-rc6: model: add multimodal embeddings (#18820)
- Ollama: 62 events in the last 90 days
- Ollama: 59th Release in the last 90 days
- Previous: earlier the same day · v0.40.0-rc5
What happened
Implements the EmbeddingGemma2Model architecture on the MLX runner: 24-layer bidirectional text encoder with PLE, shared gemma4 vision/audio towers, mean-pool + L2 output. /api/embed accepts per-item media via input dicts.
Summary assembled by rule from the sources below
Why it's spreading
Sources
Release
- v0.40.0-rc6: model: add multimodal embeddings (#18820)Ollama Releases