---
base_model:
- TeichAI/Qwen3-4B-Instruct-2507-Polaris-Alpha-Distill
- TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill
- miromind-ai/MiroThinker-4B-DPO-v0.2
- Gen-Verse/Qwen3-4B-RA-SFT
library_name: transformers
tags:
- mergekit
- merge
---

# Qwen3-4B-Architect

This model [Qwen3-4B-Architect](https://huggingface.co/nightmedia/Qwen3-4B-Architect) was created from:
- TeichAI/Qwen3-4B-Instruct-2507-Polaris-Alpha-Distill
- TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill
- miromind-ai/MiroThinker-4B-DPO-v0.2
- Gen-Verse/Qwen3-4B-RA-SFT

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Qwen3-4B-Architect")

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)
```