FUNDING · MODELS · #2041
Apertus 1.5: open-weight 8B and 70B multimodal models with 262k-token context
Apertus 1.5 extends the open-weight Apertus 1.0 family with native image and audio understanding, an optional thinking mode, improved instruction-following and tool use, and a 262,144-token context window. Updated 8B and 70B weights were published to Hugging Face under an Apache 2.0 license (July 24, 2026); the release adds trillions of continued-pretraining tokens, multimodal training, expanded evaluations, and detailed transparency on data and training.
KEY POINTS
- Apertus 1.5 extends the open-weight Apertus 1.0 family with native image and audio understanding, an optional thinking mode, improved instruction-following and tool use, and a 262,144-token context window.
- Updated 8B and 70B weights were published to Hugging Face under an Apache 2.0 license (July 24, 2026); the release adds trillions of continued-pretraining tokens, multimodal training, expanded evaluations, and detailed transparency on data and training.
- This is a major open-weight model release that adds multimodality, very long context, and permissively licensed weights, making advanced capabilities broadly accessible and reproducible.
WHY IT MATTERS
This is a major open-weight model release that adds multimodality, very long context, and permissively licensed weights, making advanced capabilities broadly accessible and reproducible.