v0.33.3-rc2: gemma4: image and audio input support
- Ollama: 24 events in the last 90 days
- Ollama: 22th Release in the last 90 days
- Previous: earlier the same day · v0.33.3-rc1
What happened
Safetensors gemma4 imports served by the MLX engine now answer image and audio chats. Images run through both vision architectures: the transformer tower (26B, 31B, e-series) and the 12B's encoder-free unified embedder. Audio arrives through the same intake the ollama API already accepts for gemma4 GGUFs — WAV bytes in the images field, OpenAI input_audio parts, and /v1/audio/transcriptions uploads — with the e2b/e4…
Summary assembled by rule from the sources below
Why it's spreading
Sources
Release
- v0.33.3-rc2: gemma4: image and audio input supportOllama Releases