---
title: UIGEN-T2-7B-mlx-4Bit
canonical_url: "https://www.modelscope.cn/models/mlx-community/UIGEN-T2-7B-mlx-4Bit"
md_url: "https://www.modelscope.cn/models/mlx-community/UIGEN-T2-7B-mlx-4Bit.md"
repository: mlx-community/UIGEN-T2-7B-mlx-4Bit
last_updated: 2025-05-12
license: apache-2.0
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen2
architectures:
  - Qwen2ForCausalLM
base_model:
  - Tesslate/UIGEN-T2-7B
base_model_relation: adapter
parameters: 1.2B
tensor_type:
  - U32
  - F16
library_name:
  - peft
  - lora
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
inference_backends:
  - "deploy_task text/emb"
  - "lmdeploy 0.9.1"
  - "lmdeploy_turbomind 0.9.1"
  - "sglang 0.5.2"
  - "vllm 0.9.2"
downloads: 329
stars: 0
tags:
  - text-generation-inference
  - transformers
  - qwen2
  - ui-generation
  - peft
  - lora
  - tailwind-css
  - html
  - mlx
  - mlx-my-repo
---

# UIGEN-T2-7B-mlx-4Bit

> UIGEN-T2-7B-mlx-4Bit - mlx-community 在 ModelScope 开源的模型。ubaitur5/UIGEN-T2-7B-mlx-4Bit

mlx-community/UIGEN-T2-7B-mlx-4Bit 是 ModelScope 魔搭社区上的 1.2B 参数text-generation模型，采用 apache-2.0 许可，基于 Tesslate/UIGEN-T2-7B 构建，可用 deploy_task text/emb、lmdeploy 0.9.1、lmdeploy_turbomind 0.9.1 部署。

- **Repository**: mlx-community/UIGEN-T2-7B-mlx-4Bit
- **License**: apache-2.0
- **Tasks**: text-generation
- **Parameters**: 1.2B
- **Base model**: Tesslate/UIGEN-T2-7B
- **Inference backends**: deploy_task text/emb, lmdeploy 0.9.1, lmdeploy_turbomind 0.9.1, sglang 0.5.2, vllm 0.9.2
- **Tags**: text-generation-inference, transformers, qwen2, ui-generation, peft, lora, tailwind-css, html, mlx, mlx-my-repo
- **Downloads**: 329
- **Stars**: 0
- **Last updated**: 2025-05-12

Source: https://www.modelscope.cn/models/mlx-community/UIGEN-T2-7B-mlx-4Bit

---

# ubaitur5/UIGEN-T2-7B-mlx-4Bit

The Model [ubaitur5/UIGEN-T2-7B-mlx-4Bit](https://huggingface.co/ubaitur5/UIGEN-T2-7B-mlx-4Bit) was converted to MLX format from [Tesslate/UIGEN-T2-7B](https://huggingface.co/Tesslate/UIGEN-T2-7B) using mlx-lm version **0.22.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("ubaitur5/UIGEN-T2-7B-mlx-4Bit")

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)
```