GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
daslab-testing
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
daslab-testing
Model Tree
swiss-ai/Apertus-8B-2509
Input Modalities
Output Modalities
Supported Functionality
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.
For more details refer to the original Apertus technical report and the new Apertus distillation technical report.
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.
bash
pip install -U transformers
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_name = "swiss-ai/Apertus-0.5B-Instruct"device = "cuda" # for GPU usage or "cpu" for CPU usage# load the tokenizer and the modeltokenizer = AutoTokenizer.from_pretrained(model_name)model = AutoModelForCausalLM.from_pretrained(model_name,).to(device)# prepare the model inputprompt = "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 outputgenerated_ids = model.generate(**model_inputs, max_new_tokens=32768)# Get and decode the outputoutput_ids = generated_ids[0][len(model_inputs.input_ids[0]) :]print(tokenizer.decode(output_ids, skip_special_tokens=True))
[!TIP] We recommend setting
temperature=0.8andtop_p=0.9in the sampling parameters.
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 |
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.
All elements used in the training process are made openly available
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.
For removal requests of personally identifiable information (PII) or of copyrighted content, please contact the respective dataset owners or us directly
To contact us, please send an email to llm-requests@swiss-ai.org
bash
@misc{TODO}
| 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 |