PulseAugur
EN
LIVE 23:02:46

Ollama adds image and audio support for Gemma4 models

By PulseAugur Editorial · [1 sources] ·

Ollama has released version v0.33.3-rc2, introducing support for image and audio input for Gemma4 models. This update leverages the MLX engine to process multimodal inputs, with images being handled by both transformer tower and unified embedder architectures, and audio processed through a dedicated intake that accepts WAV bytes and audio transcriptions. The system intelligently routes modalities to compatible checkpoints, ensuring that models without specific audio or vision capabilities function as text-only and reject unsupported input types. AI

IMPACT Enhances multimodal capabilities for local AI model deployment.

RANK_REASON This is a software release for a tool that integrates AI models, not a release of a frontier model itself.

Read on Ollama — Releases →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Ollama adds image and audio support for Gemma4 models

How we ranked this

Signal score
32 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
This is a software release for a tool that integrates AI models, not a release of a frontier model itself.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Ollama — Releases TIER_1 English(EN) · jessegross ·

    v0.33.3-rc2: gemma4: image and audio input support

    <p>Safetensors gemma4 imports served by the MLX engine now answer image<br /> and audio chats. Images run through both vision architectures: the<br /> transformer tower (26B, 31B, e-series) and the 12B's encoder-free<br /> unified embedder. Audio arrives through the same intake t…

RELATED ENTITIES

RELATED TOPICS