---
license: apache-2.0
base_model: BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32
tags:
- causal-lm
- moe
- mixture-of-experts
- qwen
- distillation
- svd
- lora-merged
- code-generation
- mlx
- mlx-my-repo
---

# jc2375/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32-mlx-4Bit

The Model [jc2375/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32-mlx-4Bit](https://huggingface.co/jc2375/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32-mlx-4Bit) was converted to MLX format from [BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32](https://huggingface.co/BasedBase/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32) using mlx-lm version **0.26.4**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("jc2375/Qwen3-30B-A3B-Thinking-2507-Deepseek-v3.1-Distill-FP32-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)
```