Understand this story
On October 15, 2026, Swiss AI released Apertus 1.5, adding native image and audio understanding capabilities on top of 1.0. The model converts images and audio into discrete tokens via early fusion and feeds them into the same sequence as text, with the architecture unchanged; it only understands multimodal input and outputs text only. The official announcement also states that Apertus 1.5 adds a thinking mode and a 262,144-token context window, four times larger than 1.0. According to the official statement, the 8B version outperforms open-source models of the same scale on instruction-following and multilingual tasks, its multimodal performance is close to Gemma 4 12B, and the training data mixture, preference data, and intermediate checkpoints for each stage are also released. There are currently no subsequent developments.
AI-generated from public reports
Latest development · Report
Swiss AI releases the Apertus 1.5 multimodal model, expanding context to 262k tokensDevelopments
1 confirmed developments
- Source:Hugging Face
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 15
Hugging FaceFirst-partySelected
Swiss AI releases the Apertus 1.5 multimodal model, expanding context to 262k tokens
Swiss AI has released Apertus 1.5, which builds on 1.0 by adding native image and audio understanding, a thinking mode, and a 262,144-token context window—4 times larger than 1.0. The model uses early fusion to convert images and audio into discrete tokens and feed them into the same sequence as text; the architecture is unchanged, and it only understands multimodal input while outputting text only. The team says the 8B version outperforms open-source models of the same scale on instruction following and multilingual tasks, its multimodal performance is close to Gemma 4 12B, and it has also released the training data mixture, preference data, and intermediate checkpoints from each stage.