# Apertus 1.5 adds multimodal understanding, 4x context window to open-weights LLMs

> **Key takeaway:** Swiss AI's Apertus 1.5 extends its 8B and 70B open-weights models with native image/audio understanding, a 262k-token context window, optional chain-of-thought reasoning, and improved tool use, trained on 4T additional tokens for the 8B model and 2T for the 70B.

**Published:** 2026-10-15T09:08:45+00:00 
**Source:** Hugging Face Blog & Announcements 
**Category:** ai-open-models 
**Canonical URL:** https://fosswire.org/news/apertus-15-adds-multimodal-understanding-4x-context-window-t.html 

## Summary
Apertus 1.5, released by Swiss AI on Hugging Face under Apache 2.0, upgrades the project's 8B and 70B parameter models with multimodal input capabilities through early-fusion tokenization. The context window expands from 65k to 262,144 tokens. A new optional thinking mode improves reasoning performance on benchmarks like AIME. The release maintains the project's fully open approach: weights, training data, and evaluation details are all published.

## How Apertus 1.5 handles multimodality
- **Early-fusion architecture**: Images and audio are tokenized directly into the text sequence rather than using a separate vision encoder. Images use Emu3.5 tokenizer (512×512 → 1,024 tokens); audio uses WavTokenizer at 40 tokens/second.
- **Vocabulary-only extension**: The transformer architecture is unchanged; training speed matches text-only models.
- **Four-stage continued pretraining**: Unpaired modalities → paired alignment → cooldown with higher-quality math/code data → gradual long-context scaling from 8k to 262k tokens.
- **Five-stage post-training**: SFT (3.7M samples) → long-context SFT → RL with verifiable rewards (350k prompts) → DPO with judge-scored preferences → SDPO charter alignment.
- **Training scale**: 8B model reaches 19T total tokens; 70B model reaches 17T total tokens.

## Why it matters
The release demonstrates that fully open model development—including published weights, data, and evaluation infrastructure—can remain competitive with partially open alternatives on multimodal and multilingual tasks. The EvalEval/EEE integration may influence how other open model projects report benchmark results.