---
title: Minitron-4B-Base
canonical_url: "https://www.modelscope.cn/models/mlx-community/Minitron-4B-Base"
md_url: "https://www.modelscope.cn/models/mlx-community/Minitron-4B-Base.md"
repository: mlx-community/Minitron-4B-Base
last_updated: 2024-12-19
model_type:
  - nemotron
architectures:
  - NemotronForCausalLM
parameters: 4.2B
tensor_type:
  - F16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "vllm 0.9.2"
downloads: 993
stars: 0
---

# Minitron-4B-Base

> Minitron-4B-Base - mlx-community 在 ModelScope 开源的模型。mlx-community/Minitron-4B-Base

mlx-community/Minitron-4B-Base 是 ModelScope 魔搭社区上的 4.2B 参数机器学习模型，可用 deploy_task text/emb、vllm 0.9.2 部署。

- **Repository**: mlx-community/Minitron-4B-Base
- **Parameters**: 4.2B
- **Inference backends**: deploy_task text/emb, vllm 0.9.2
- **Downloads**: 993
- **Stars**: 0
- **Last updated**: 2024-12-19

Source: https://www.modelscope.cn/models/mlx-community/Minitron-4B-Base

---

# mlx-community/Minitron-4B-Base

The Model [mlx-community/Minitron-4B-Base](https://huggingface.co/mlx-community/Minitron-4B-Base) was converted to MLX format from [nvidia/Minitron-4B-Base](https://huggingface.co/nvidia/Minitron-4B-Base) using mlx-lm version **0.17.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Minitron-4B-Base")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```