---
title: MiniCPM5-1B-mlx-6Bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/MiniCPM5-1B-mlx-6Bit"
md_url: "https://www.modelscope.cn/models/mlx-community/MiniCPM5-1B-mlx-6Bit.md"
repository: mlx-community/MiniCPM5-1B-mlx-6Bit
last_updated: 2026-09-10
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - llama
architectures:
  - LlamaForCausalLM
base_model:
  - openbmb/MiniCPM5-1B
base_model_relation: quantized
parameters: 236.4M
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
downloads: 6
stars: 0
tags:
  - minicpm
  - minicpm5
  - llama
  - text-generation
  - long-context
  - tool-calling
  - on-device
  - edge-ai
  - mlx
  - mlx-my-repo
---

# MiniCPM5-1B-mlx-6Bit

> MiniCPM5-1B-mlx-6Bit - mlx-community 在 ModelScope 开源的模型。adrgrondin/MiniCPM5-1B-mlx-6Bit

mlx-community/MiniCPM5-1B-mlx-6Bit 是 ModelScope 魔搭社区上的 236.4M 参数text-generation模型，采用 apache-2.0 许可，基于 openbmb/MiniCPM5-1B 构建。

- **Repository**: mlx-community/MiniCPM5-1B-mlx-6Bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 236.4M
- **Base model**: openbmb/MiniCPM5-1B
- **Tags**: minicpm, minicpm5, llama, text-generation, long-context, tool-calling, on-device, edge-ai, mlx, mlx-my-repo
- **Downloads**: 6
- **Stars**: 0
- **Last updated**: 2026-09-10

Source: https://www.modelscope.cn/models/mlx-community/MiniCPM5-1B-mlx-6Bit

---

# adrgrondin/MiniCPM5-1B-mlx-6Bit

The Model [adrgrondin/MiniCPM5-1B-mlx-6Bit](https://huggingface.co/adrgrondin/MiniCPM5-1B-mlx-6Bit) was converted to MLX format from [openbmb/MiniCPM5-1B](https://huggingface.co/openbmb/MiniCPM5-1B) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("adrgrondin/MiniCPM5-1B-mlx-6Bit")

prompt="hello"

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

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