---
license: apache-2.0
tags:
- merge
- mergekit
- lazymergekit
- qwen3
- ZeroXClem
- hermes
- SkyHighHermes
- Heretic
- Abliterated
- HighReasoning
- Distilled
- Claude
- mlx
base_model: ZeroXClem/Qwen3-4B-Sky-High-Hermes
pipeline_tag: text-generation
library_name: mlx
---

# Qwen3-4B-Sky-High-Hermes-qx86-hi-mlx

> Brainwave: 0.430,0.490,0.710,0.608,0.372,0.733,0.627

That image on the model card... epic :)


This model [Qwen3-4B-Sky-High-Hermes-qx86-hi-mlx](https://huggingface.co/nightmedia/Qwen3-4B-Sky-High-Hermes-qx86-hi-mlx) was
converted to MLX format from [ZeroXClem/Qwen3-4B-Sky-High-Hermes](https://huggingface.co/ZeroXClem/Qwen3-4B-Sky-High-Hermes)
using mlx-lm version **0.30.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Qwen3-4B-Sky-High-Hermes-qx86-hi-mlx")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```