Apertus Base model:finetune:swiss-ai/a... Base model:swiss-ai/apertus-8b... Compliant Conversational Instruct Mlx Multilingual Region:us Safetensors Sharded Swiss-ai Tensorflow
Model Card on HF 🤗: https://huggingface.co/mlx-community/Apertus-8B-Instruct-2509-bf16
Apertus 8B Instruct 2509 Bf16 Benchmarks
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
What is the LLM Explorer Rank (Score)
Apertus 8B Instruct 2509 Bf16 Parameters and Internals
| LLM Name | Apertus 8B Instruct 2509 Bf16 |
| Repository 🤗 | https://huggingface.co/mlx-community/Apertus-8B-Instruct-2509-bf16 |
| Base Model(s) | |
| Model Size | 8b |
| Required VRAM | 16.1 GB |
| Updated | 2025-09-06 |
| Maintainer | mlx-community |
| Model Type | apertus |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | ApertusForCausalLM |
| License | apache-2.0 |
| Context Length | 65536 |
| Model Max Length | 65536 |
| Transformers Version | 4.56.0.dev0 |
| Tokenizer Class | PreTrainedTokenizer |
| Padding Token | <pad> |
| Vocabulary Size | 131072 |
Best Alternatives to Apertus 8B Instruct 2509 Bf16
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| ...ertus 8B Instruct 2509 Ungated | 64K / 16.1 GB | 58 | 2 |
Rank the Apertus 8B Instruct 2509 Bf16 Capabilities
🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟
What open-source LLMs or SLMs are you in search of? 51147 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124