---
title: Minitron-4B-Base-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/Minitron-4B-Base-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/Minitron-4B-Base-4bit.md"
repository: mlx-community/Minitron-4B-Base-4bit
last_updated: 2024-12-19
model_type:
  - nemotron
architectures:
  - NemotronForCausalLM
parameters: 655.1M
tensor_type:
  - F16
  - U32
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
inference_backends:
  - "deploy_task text/emb"
  - "vllm 0.9.2"
downloads: 991
stars: 0
---

# Minitron-4B-Base-4bit

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

mlx-community/Minitron-4B-Base-4bit 是 ModelScope 魔搭社区上的 655.1M 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-4bit
- **Parameters**: 655.1M
- **Inference backends**: deploy_task text/emb, vllm 0.9.2
- **Downloads**: 991
- **Stars**: 0
- **Last updated**: 2024-12-19

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

---

# mlx-community/Minitron-4B-Base-4bit

The Model [mlx-community/Minitron-4B-Base-4bit](https://huggingface.co/mlx-community/Minitron-4B-Base-4bit) 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-4bit")
response = generate(model, tokenizer, prompt="hello", verbose=True)
```