---
type: "post"
id: "apertus-1-5-release-notes-analysis-7dac13"
slug: "apertus-1-5-release-notes-analysis-7dac13"
title: "Apertus 1.5 Release Notes"
description: "Apertus 1.5 makes multimodality a tokenizer-level extension to an existing open model rather than a separate vision stack."
retrieval_nugget: "Apertus 1.5 makes multimodality a tokenizer-level extension to an existing open model rather than a separate vision stack."
published_at: "2026-10-15"
updated_at: "2026-10-15"
record_date: "2026-10-15"
date_kind: "published_at"
topics: ["multimodal","open-models","models"]
source_urls: ["https://huggingface.co/blog/swiss-ai/apertus-v15-release-notes"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:apertus-1-5-release-notes-analysis-7dac13"
status: "published"
visuals: []
editorial_provenance: {"schema_version":"newruntime-editorial-copy-v1","content_status":"source_grounded_final","final_copy_sha256":"sha256:366c2eea925b7743abcf17ba1253a9dffc39f13113c27f66b35ead184c8df4e2","reviewed_at":"2026-10-15T14:01:14.343Z","source_evidence_count":1,"verified_claim_count":3,"site_analysis_schema_version":"newruntime-site-analysis-v1","site_object_kind":"field_note","observed_fact_count":3,"implication_count":2,"watch_condition_count":1,"related_record_count":0}
analysis: {"schema_version":"newruntime-site-analysis-v1","object_kind":"field_note","thesis":"Apertus 1.5 extends an established open-model family by adding image and audio input through shared token sequences, while keeping the model architecture unchanged.","observed_facts":[{"text":"The release extends the Apertus 1.0 8B and 70B models and describes image and audio inputs as discrete tokens in the same sequence as text, without a separate vision encoder.","source_urls":["https://huggingface.co/blog/swiss-ai/apertus-v15-release-notes"]},{"text":"The source states that the context window is 262,144 tokens and that the models understand images and audio but generate only text.","source_urls":["https://huggingface.co/blog/swiss-ai/apertus-v15-release-notes"]},{"text":"The post says weights were released under Apache 2.0 and lists training recipes, data transparency records, intermediate checkpoints, and evaluation materials.","source_urls":["https://huggingface.co/blog/swiss-ai/apertus-v15-release-notes"]}],"mechanism":"Image and audio are tokenized into the existing sequence alongside text, adding input modalities without an architectural change.","why_now":"The release pairs these capability changes with a public account of the training pipeline and evaluation evidence.","implications":["For teams evaluating open models, the release offers a practical route to test image- and audio-grounded workflows alongside long-context text tasks.","Public recipes and checkpoints make the reported development process more inspectable and potentially reproducible."],"evidence_boundary":"The supplied source documents the release and its authors’ claims, but does not independently validate benchmark results or deployment quality.","watch_conditions":["Watch whether independent evaluations and real deployments confirm the reported multimodal and tool-use gains."],"related_records":[],"new_branch_reason":"No prior New Runtime analytical record is supplied for this specific release; this note opens a distinct record focused on tokenizer-level multimodal extension and the release’s disclosed evidence."}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/apertus-1-5-release-notes-analysis-7dac13/","markdown":"https://newruntime.com/posts/apertus-1-5-release-notes-analysis-7dac13.md","json":"https://newruntime.com/posts/apertus-1-5-release-notes-analysis-7dac13.json"}
---

# Apertus 1.5 Release Notes

## Retrieval answer

Apertus 1.5 makes multimodality a tokenizer-level extension to an existing open model rather than a separate vision stack.

Apertus 1.5 makes multimodality a tokenizer-level extension to an existing open model rather than a separate vision stack. The exact thesis is: “Apertus 1.5 extends an established open-model family by adding image and audio input through shared token sequences, while keeping the model architecture unchanged.” The source says images and audio enter the same sequence as text tokens, with no separate vision encoder; the models understand these inputs but generate only text.

The mechanism matters because it broadens the kinds of material the model can interpret without changing the architectural boundary. The team reports 4 trillion added tokens for 8B and 2 trillion for 70B, extending the 1.0 models, and a context window of 262,144 tokens. Mechanism: Image and audio are tokenized into the existing sequence alongside text, adding input modalities without an architectural change. Why now: “The release pairs these capability changes with a public account of the training pipeline and evaluation evidence.” The post lists training stages, data transparency records, intermediate checkpoints, recipes, and evaluation materials. We can therefore inspect more than a headline capability claim, though the source remains the project’s own account.

The first implication is: “For teams evaluating open models, the release offers a practical route to test image- and audio-grounded workflows alongside long-context text tasks.” The project says its performance still trails frontier open-weight models overall, while reporting strengths in selected tasks; those comparisons should be treated as the authors’ evaluation, not an independent verification here. The evidence boundary is: “The supplied source documents the release and its authors’ claims, but does not independently validate benchmark results or deployment quality.” The first watch condition is: “Watch whether independent evaluations and real deployments confirm the reported multimodal and tool-use gains.”

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Multimodal](https://newruntime.com/topics/multimodal.md): Explore the multimodal topic hub.
- topic hub: [Open Models](https://newruntime.com/topics/open-models.md): Explore the open-models topic hub.
- topic hub: [Models](https://newruntime.com/topics/models.md): Explore the models topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)