Apertus-v1.5-70B-base

Apertus 1.5 is a family of 8B and 70B fully open, multilingual, and multimodal models from the Swiss AI Initiative, trained only on openly available data and released with open weights, open data, and open training documentation. The models cover a large variety of languages, handle contexts up to 262,144 tokens, accept image and audio input, and support a thinking mode for reasoning tasks.

This checkpoint is the long context extended model of the 70B pre-training pipeline.

How to Use

This is a base model without a chat template: use plain-text completion. For the instruction-tuned model, see swiss-ai/Apertus-v1.5-70B.

Installation

VLLM_USE_PRECOMPILED=1 \
VLLM_PRECOMPILED_WHEEL_COMMIT=8700f86a7012b2354c3f2834c1a0d2b6023b0bcd \
pip install "vllm @ git+https://github.com/swiss-ai/vllm.git@b84ba28e5ed19c08e09a9f2561451001b65aaa0e"

pip install "transformers[torch,vision,audio] @ git+https://github.com/swiss-ai/transformers.git@0c5e12f18a5ff5c93cb1ef755aebbd557e26e884"

vLLM

from vllm import LLM, SamplingParams

llm = LLM(model="swiss-ai/Apertus-v1.5-70B-base", tensor_parallel_size=4)
outputs = llm.generate(["The capital of Switzerland is"], SamplingParams(max_tokens=64))
print(outputs[0].outputs[0].text)

Transformers

import torch
from transformers import AutoModelForMultimodalLM, AutoProcessor

MODEL_ID = "swiss-ai/Apertus-v1.5-70B-base"

processor = AutoProcessor.from_pretrained(MODEL_ID)
model = AutoModelForMultimodalLM.from_pretrained(MODEL_ID, dtype="auto", device_map="auto")

inputs = processor(text="The capital of Switzerland is", return_tensors="pt").to(model.device)
with torch.inference_mode():
    output_ids = model.generate(**inputs, max_new_tokens=64)
print(processor.decode(output_ids[0, inputs["input_ids"].shape[-1]:], skip_special_tokens=True))

For image or audio input, add an <|image|> or <|audio|> placeholder to the text and pass images=[...] or audio=[...] to the processor.

Evaluations

Limitations

Apertus can produce text on a variety of topics, but the generated content may not always be factually accurate, logically consistent, or free from biases present in the training data. These models should be used as assistive tools rather than definitive sources of information. Users should always verify important information and critically evaluate any generated content.

See the Apertus Charter for the alignment principles that govern the responses of the models.

License

Apache 2.0.

Legal and Compliance

By using the Apertus LLM you agree to indemnify, defend, and hold harmless ETH Zurich and EPFL against any third-party claims arising from your use of Apertus LLM.

EU AI Act documentation (Apertus_1_5_EU_Public_Summary.pdf and Apertus_1_5_EU_Code_of_Practice.pdf) is available at https://github.com/swiss-ai/apertus-legal/, alongside the usage policy and privacy policy.

We strongly advise downloading and updating new model weights from this site every six months.

Data protection contacts: llm-privacy-requests@swiss-ai.org and llm-copyright-requests@swiss-ai.org.

Contact

General inquiries: llm-requests@swiss-ai.org, or https://apertus-ai.org/contact/.

Citation

@techreport{apertus15,
  title  = {Apertus 1.5},
  author = {Project Apertus},
  year   = {2026},
}