Apertus-0.5B-Instruct

Table of Contents

1. Model Summary
2. How to use
3. Evaluation
4. Training
5. Limitations
6. Legal Aspects

---

Model Summary

Apertus-0.5B-Instruct is a highly efficient, sub-billion parameter language model designed to extend the fully-open and compliant Apertus ecosystem to highly constrained hardware environments.

The model relies on a dense transformer architecture featuring grouped-query attention and xIELU activations. To achieve high performance with a minimized memory footprint, it uses tied embeddings and a deeper, thinner architectural design.

Instead of standard pre-training, Apertus-0.5B-Instruct was created using pre-training distillation (PD) from the Apertus-8B-Instruct-2509 teacher model. It was trained on 1.7T tokens from Phase 5 of the original Apertus data pipeline—the highest quality tier of filtered documents, code, and instruction samples. Post-training included supervised fine-tuning (SFT) and alignment similar to that of the original Apertus.

Key features

• Fully open model: open weights + open data + full training details including all data and training recipes
• Massively Multilingual: 1811 natively supported languages
• Compliant Apertus is trained while respecting opt-out consent of data owners (even retrospectivey), and avoiding memorization of training data
• Cost-Effective Distillation: Trained using a 90%/10% mix of KL-Divergence and label cross-entropy derived from the 8B teacher model, drastically reducing the required compute.
• Hardware Optimized: Specifically optimized for memory-limited scenarios like mobile and edge deployments, with quantized checkpoints available for Apple devices (MLX) in INT2, INT3, INT4, and INT6 formats.

For more details refer to the original Apertus technical report and the new Apertus distillation technical report.

---

How to use

The modeling code for Apertus is available in transformers v4.56.0 and later, so make sure to upgrade your transformers version. You can also load the model with the latest vLLM which uses transformers as a backend.

pip install -U transformers

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "swiss-ai/Apertus-0.5B-Instruct"
device = "cuda"  # for GPU usage or "cpu" for CPU usage

# load the tokenizer and the model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
).to(device)

# prepare the model input
prompt = "Give me a brief explanation of gravity in simple terms."
messages_think = [
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages_think,
    tokenize=False,
    add_generation_prompt=True,
)
model_inputs = tokenizer([text], return_tensors="pt", add_special_tokens=False).to(model.device)

# Generate the output
generated_ids = model.generate(**model_inputs, max_new_tokens=32768)

# Get and decode the output
output_ids = generated_ids[0][len(model_inputs.input_ids[0]) :]
print(tokenizer.decode(output_ids, skip_special_tokens=True))

We recommend setting temperature=0.8 and top_p=0.9 in the sampling parameters.

---

Evaluation

Post-Training Multilingual Evaluation: Performance of the Apertus-0.5B-Instruct model across multilingual benchmarks compared to models in similar size classes.

Model	Average	MMLU	TruthfulQA	Arc	IF	LogiQA
Apertus-0.5B-Instruct	0.318	0.258	0.461	0.225	0.328	0.279
gemma-3-270m-it	0.289	0.242	0.465	0.215	0.236	0.205
Qwen3-0.6B	0.401	0.377	0.464	0.222	0.541	0.353
gemma-3-1b-it	0.406	0.409	0.457	0.250	0.509	0.379
EuroLLM-1.7B-Instruct	0.291	0.260	0.433	0.250	0.222	0.269

While Apertus-0.5B-Instruct demonstrates competitive baseline multilingual chatting performance, it may lack in specific capabilities such as advanced math and complex instruction following due to its highly constrained parameter count.

---

Training

Model Architecture

• Architecture Type: Dense transformer decoder with grouped-query attention.
• Layers: 20.
• Model Dimension: 1024.
• MLP Dimension: 6144.
• Heads (Q/KV): 16/4.
• Tied Embeddings: Yes.
• Activation Function: xIELU.
• Compute / Storage Size: 0.4B parameters.

Pre-Training Details

• Training Tokens: 1.7T.
• Optimizer: AdEMAMix with WSD schedule and weight decay.
• Sequence Handling: Documents packed into chunks of 4096 tokens with cross-document attention masked.
• Total Compute: 0.2E22 FLOPs.

Software & hardware

• GPUs: 64 GH200
• Training Framework: Megatron-LM

Open resources

All elements used in the training process are made openly available

• Training data reconstruction scripts: github.com/swiss-ai/pretrain-data
• The training intermediate checkpoints are available on the different branches of this same repository

---

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.

---

Legal Aspects

EU AI Act Transparency Documentation and Code of Practice

• Apertus_EU_Public_Summary.pdf
• Apertus_EU_Code_of_Practice.pdf

Data Protection and Copyright Requests

For removal requests of personally identifiable information (PII) or of copyrighted content, please contact the respective dataset owners or us directly

• llm-privacy-requests@swiss-ai.org
• llm-copyright-requests@swiss-ai.org

Output Filter for PII

• Currently no output filter is provided.
• Please check this site regularly for an output filter that can be used on top of the Apertus LLM. The filter reflects data protection deletion requests which have been addressed to us as the developer of the Apertus LLM. It allows you to remove Personal Data contained in the model output. We strongly advise downloading and applying this output filter from this site every six months.

Contact

To contact us, please send an email to llm-requests@swiss-ai.org

Citation

@misc{TODO}