Apertus 1.5 expands 8B and 70B models with image and audio understanding
🎧 Listen to this story
The Apertus project released the weights of its 8B and 70B Apertus 1.5 models on Hugging Face on July 24, 2026, under an Apache 2.0 license. The update adds native image and audio understanding, an optional thinking mode, improved instruction-following and tool use, and expands the context window fourfold to 262,144 tokens. Spoken language remains experimental, and the models generate text only.
Apertus 1.5 is a continuation of pretraining, with 4 trillion additional tokens for the 8B model and 2 trillion for the 70B model, bringing their totals to 19 trillion and 17 trillion, respectively. The project says the models keep their weights, data, values and training details open; the process included multimodal training, long-context data and supervised fine-tuning, reinforcement learning, DPO and alignment with the Apertus Charter.
Why it matters · editorial interpretation
The combination of open weights, native image and audio input, and a 262,144-token context window could expand how researchers and developers evaluate and adapt these models. Because the project says it keeps the data, values, and training details open, the update also offers more material for studying how multimodal models are built and aligned.