---
title: SciPhi-Triplex-4bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/SciPhi-Triplex-4bit"
md_url: "https://www.modelscope.cn/models/mlx-community/SciPhi-Triplex-4bit.md"
repository: mlx-community/SciPhi-Triplex-4bit
last_updated: 2026-06-26
license: cc-by-nc-sa-4.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - phi3
architectures:
  - Phi3ForCausalLM
base_model:
  - SciPhi/Triplex
base_model_relation: quantized
parameters: 597.2M
tensor_type:
  - BF16
  - U32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 21
stars: 0
tags:
  - mlx
---

# SciPhi-Triplex-4bit

> SciPhi-Triplex-4bit - mlx-community 在 ModelScope 开源的模型。mlx-community/SciPhi-Triplex-4bit

mlx-community/SciPhi-Triplex-4bit 是 ModelScope 魔搭社区上的 597.2M 参数text-generation模型，采用 cc-by-nc-sa-4.0 许可，基于 SciPhi/Triplex 构建。

- **Repository**: mlx-community/SciPhi-Triplex-4bit
- **License**: cc-by-nc-sa-4.0
- **Tasks**: text-generation
- **Parameters**: 597.2M
- **Base model**: SciPhi/Triplex
- **Tags**: mlx
- **Downloads**: 21
- **Stars**: 0
- **Last updated**: 2026-06-26

Source: https://www.modelscope.cn/models/mlx-community/SciPhi-Triplex-4bit

---

# mlx-community/SciPhi-Triplex-4bit

This model [mlx-community/SciPhi-Triplex-4bit](https://huggingface.co/mlx-community/SciPhi-Triplex-4bit) was
converted to MLX format from [SciPhi/Triplex](https://huggingface.co/SciPhi/Triplex)
using mlx-lm version **0.29.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/SciPhi-Triplex-4bit")

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)
```