Project AURIONAI Use-Cases Research & Innovation
LLM

Apertus 70B Instruct (Apertus-70B-Instruct-2509)

Instruction-tuned 70B Apertus model from the Swiss AI Initiative, built for massively multilingual text generation with open weights.

Swiss AI (EPFL, ETH Zurich, CSCS)
Levelmodel
ClassLLM
Parameters70B
Context65,536
Released2 Sep 2025
Opennessopen weights permissive
Runs onnot in the notes
Statusactive

Lineage

instruct of
Swiss AI (EPFL, ETH Zurich, CSCS)Apertus-70B-2509 is the parent (instruct of)high confidencemodel card
Where this comes from
Parent and child relations from model cards, Hugging Face base_model fields and the genealogy tables of the research notes. The tree shows two generations each way, 2 models. Confidence and evidence are the notes' own.

R&D Topics

Identity

Developer
Swiss AI (EPFL, ETH Zurich, CSCS)
Family
Apertus
Released
2 Sep 2025 sourcessecondary report
Weights published
–
Record checked
11 Oct 2026
Where this comes from
Developer and dates from the research notes. Release date is the vendor's public announcement; weights date is when open weights were published.

Architecture and Size

Architecture
dense transformer Decoder-only transformer with xIELU activation, trained with the AdEMAMix optimizer
Total parameters
70B sources
Active parameters
–
Checkpoint parameters
–
Note
Card says 70B; safetensors metadata lists 71B
Context length
65,536 tokens
Input
text
Output
text
Where this comes from
Parameter counts as the developer states them. Where the checkpoint holds a different total, both are shown (register A16).

Openness and Access

Openness
open weights permissive
Licence
Apache License 2.0 sources
Access routes
open weights download
Where this comes from
The licence file governs over registry tags and aggregator labels.

Deployment

Runs on
not in the notes
Footprint
not in the notes
Runtimes
not in the notes
Where this comes from
Deployment tiers and runtimes as named in the notes. Footprint is the notes' figure, not a measurement by AURION.

Indonesia

Indonesian support
not stated
Regional languages
not in the notes
Jakarta hosting
unknown
Languages
Card states 1811 natively supported languages; Indonesian not named
Where this comes from
Indonesia fields are carried on every model; unknown is an allowed value.

Benchmark Results

The notes record no benchmark result for this model.

Industry Use Cases

No industry use case links this model.

Sources

  1. huggingface.co/swiss-ai/Apertus-70B-Instruct-2509 https://huggingface.co/swiss-ai/Apertus-70B-Instruct-2509
  2. artificialanalysis.ai/models/apertus-70b-instruct https://artificialanalysis.ai/models/apertus-70b-instruct

To cite this page: Project AURION, AI Use-Cases Research & Innovation, "Apertus 70B Instruct (Apertus-70B-Instruct-2509)", https://aurion.semai.id/models/swiss-ai-apertus-70b-instruct-2509/, records of October 2026.