---
title: Apertus-8B-2509-bf16
canonical_url: "https://www.modelscope.cn/models/mlx-community/Apertus-8B-2509-bf16"
md_url: "https://www.modelscope.cn/models/mlx-community/Apertus-8B-2509-bf16.md"
repository: mlx-community/Apertus-8B-2509-bf16
last_updated: 2025-09-03
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - apertus
architectures:
  - ApertusForCausalLM
base_model:
  - swiss-ai/Apertus-8B-2509
base_model_relation: finetune
parameters: 8.1B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 87
stars: 0
tags:
  - multilingual
  - compliant
  - swiss-ai
  - apertus
  - mlx
---

# Apertus-8B-2509-bf16

> Apertus-8B-2509-bf16 - mlx-community 在 ModelScope 开源的模型。mlx-community/Apertus-8B-2509-bf16

mlx-community/Apertus-8B-2509-bf16 是 ModelScope 魔搭社区上的 8.1B 参数text-generation模型，采用 apache-2.0 许可，基于 swiss-ai/Apertus-8B-2509 构建。

- **Repository**: mlx-community/Apertus-8B-2509-bf16
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 8.1B
- **Base model**: swiss-ai/Apertus-8B-2509
- **Tags**: multilingual, compliant, swiss-ai, apertus, mlx
- **Downloads**: 87
- **Stars**: 0
- **Last updated**: 2025-09-03

Source: https://www.modelscope.cn/models/mlx-community/Apertus-8B-2509-bf16

---

# mlx-community/Apertus-8B-2509-bf16

This model [mlx-community/Apertus-8B-2509-bf16](https://huggingface.co/mlx-community/Apertus-8B-2509-bf16) was
converted to MLX format from [swiss-ai/Apertus-8B-2509](https://huggingface.co/swiss-ai/Apertus-8B-2509)
using mlx-lm version **0.27.0**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Apertus-8B-2509-bf16")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```