TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

Apertus 8B 2509

Apertus 8B 2509 is a fully open multilingual language model developed by the Swiss AI Initiative, featuring 8 billion parameters trained on 15 trillion tokens with a staged curriculum of web, code, and math data. Built as a transformer decoder, it uses a novel xIELU activation function and was trained with the AdEMAMix optimizer, followed by supervised fine-tuning and alignment via QRPO.

The model natively supports over 1800 languages and delivers long context processing up to 65,536 tokens, tool use, and agentic capabilities. Apertus stands out for its full openness: open weights, open training data, full training recipes, and compliance with data owner opt-out consent even retroactively.

On general language understanding benchmarks, Apertus 8B achieves 65.8% average across ARC, HellaSwag, WinoGrande, XNLI, XCOPA, and PIQA — comparable to Llama 3.1-8B (65.4%) while being fully open. Licensed under Apache 2.0.
Text Gen 7
Released: September 17, 2025

Overview

Apertus 8B 2509 is a fully open 8B parameter language model by Swiss AI Initiative, pretrained on 15T tokens. It natively supports over 1800 languages including all Swiss national languages, uses only compliant open training data, and achieves performance comparable to closed-source models. Supports long context up to 65K tokens and tool use.

About Swiss AI Initiative

The Swiss AI Initiative is the world's largest open science/open source effort for AI foundation models, started in December 2023. Seeded with over 10M GPU hours on the Alps supercomputer and a 20M CHF grant from the ETH Domain, it is the first initiative of the Swiss National AI Institute—a partnership between the ETH AI Center and the EPFL AI Center—leveraging 800+ researchers (70 AI-focused professors) from 10+ Swiss academic institutions.

Industry: Research
Location: Zürich, CH
View Company Profile
Last updated: June 30, 2026
0 AIs selected
Clear selection
#
Name
Task