Apertus 1.5 Open-Source Release Adds Image, Audio and 262K Context

Swiss AI team released Apertus 1.5 (8B/70B, Apache 2.0), a continued pretraining upgrade adding 4T/2T tokens, image and experimental audio input, optional thinking mode, and a 262,144-token context window, with a fully reproducible release note on Hugging Face.

2026-10-17 ~ 2026-10-17 · 2 related posts

• Swiss team's open Apertus 1.5 adds multimodal input and 262K context, with all training checkpoints public — lmoroney · 2026-10-17
• Apertus 1.5 release notes: 19T/17T total training tokens, fully open weights, data and recipes — lmoroney · 2026-10-17