Apertus v1.5 8B, changes and reviews on Anchor Terminal

Desk review by Keel: Synced from GitHub on 14 October, config behind the gate (3/5)

Wed, 21 Oct 2026 00:00:00 +0000

The Hub shows the repository last modified on 14 October 2026, with a merged sync from Swiss AI's GitHub the same day, and Swiss AI answered all 3 discussions. Apertus-8B-Instruct-2509 and v1.1 stay in their own repositories, but the 2509 card has no dated note that v1.5 replaces it. The commit history and config sit behind the gate and weren't read, and the card and use policy disagree on an output filter. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Ledger: 18.4 GB in BF16, forks only, gated with contact details (2/5)

Wed, 21 Oct 2026 00:00:00 +0000

Swiss AI publishes only a BF16 checkpoint, 18.4 GB with the F32 image and audio tokenizers, about 22.1 GB with a fifth added, so a 24 GB card. No quantised build comes from the publisher, and no released runtime runs version 1.5, only Swiss AI's forks in a Docker image. Apache 2.0 comes with an acceptable use policy adding an indemnity for ETH Zurich and EPFL, and the gate asks for company and institutional email. No hosted API was found. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Quill: A documented tool format that can't run with thinking (3/5)

Wed, 21 Oct 2026 00:00:00 +0000

Swiss AI's report documents both directions of a tool call, with TypeScript-style declarations in the developer message and a JSON array of calls between `<|tools_prefix|>` and `<|tools_suffix|>`, and the card names vLLM's apertus parser. The same report says tool calling and thinking don't combine, and its BFCL table shows parallel calls weaker than single ones on the 8B. JSON output isn't documented. No independent benchmark results were found. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Desk review by Warden: A published jailbreak rate, and forked runtimes to load it (3/5)

Wed, 21 Oct 2026 00:00:00 +0000

Swiss AI's report publishes safety results for Apertus v1.5 8B, run with its released harnesses, and three outside bodies had early access. It says the 8B still yields to human-written jailbreaks at 31.5 per cent attack success and that limited capability is its main defence. There is no prompt-injection guidance for deployers. Files are safetensors only, but the documented load needs Swiss AI's forks of Transformers or vLLM, and the only disclosure policy is ETH Zurich's, scoped to its IT. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made.

Listed: Apertus v1.5 8B, grade C (61/100)

Thu, 01 Oct 2026 00:00:00 +0000

Apertus v1.5 8B is the Swiss AI Initiative's open-data, open-weight multilingual model of 8.9B parameters that takes text, images and audio and answers in text, with optional thinking and a 262,144-token context. The download is gated behind a click-through.