---
language:
- en
- ja
pipeline_tag: image-text-to-text
tags:
- mlx
- mlx-vlm
- qwen3_5
- vision-language
- function-calling
library_name: mlx
license: apache-2.0
base_model: empero-ai/Qwythos-9B-Claude-Mythos-5-1M
---

# Qwythos-9B-Claude-Mythos-5-1M MLX (4bit, noident)

A conversion of [`empero-ai/Qwythos-9B-Claude-Mythos-5-1M`](https://huggingface.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M) to Apple's [MLX](https://github.com/ml-explore/mlx) format, **quantized to 4bit**.

- Conversion tool: [mlx-maker](https://github.com/ToPo-ToPo) / `mlx-vlm`
- Source model: [`empero-ai/Qwythos-9B-Claude-Mythos-5-1M`](https://huggingface.co/empero-ai/Qwythos-9B-Claude-Mythos-5-1M)
- Base model: [`Qwen/Qwen3.5-9B`](https://huggingface.co/Qwen/Qwen3.5-9B)
- License: Apache-2.0 (inherited from the source model)

## About the chat template

**Modified variant**: both the forced identity and the default system prompt have been completely removed from `chat_template.jinja`. A system block is emitted only when the caller provides one. **The weights are unchanged** and identical to the same-quantization base variant.

## Usage (mlx-vlm)

```bash
uv add mlx-vlm
```

```python
from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template

model, processor = load("ToPo-ToPo/Qwythos-9B-Claude-Mythos-5-1M-mlx-4bit-noident")
messages = [{"role": "user", "content": "Hello"}]
prompt = apply_chat_template(processor, model.config, messages)
print(generate(model, processor, prompt, max_tokens=256))
```


---

This repository is a derivative work distributed under Apache-2.0. The original
attribution and license are inherited as noted above.