---
title: QwenPaw-Flash-9B-heretic-mlx-8Bit
canonical_url: "https://www.modelscope.ai/models/SC117/QwenPaw-Flash-9B-heretic-mlx-8Bit"
md_url: "https://www.modelscope.ai/models/SC117/QwenPaw-Flash-9B-heretic-mlx-8Bit.md"
repository: SC117/QwenPaw-Flash-9B-heretic-mlx-8Bit
last_updated: 2026-10-04
license: other
pipeline_tag: text-generation
tasks:
  - text-generation
model_type:
  - qwen3_5
architectures:
  - Qwen3_5ForConditionalGeneration
base_model:
  - SC117/QwenPaw-Flash-9B-heretic
base_model_relation: quantized
parameters: 2.5B
tensor_type:
  - U32
  - F32
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - zh
downloads: 134
stars: 0
tags:
  - mlx
---

# QwenPaw-Flash-9B-heretic-mlx-8Bit

> QwenPaw-Flash-9B-heretic-mlx-8Bit - An open-source model by SC117 on ModelScope. SC117/QwenPaw-Flash-9B-heretic-mlx-8Bit

SC117/QwenPaw-Flash-9B-heretic-mlx-8Bit is a 2.5B-parameter text-generation model on ModelScope. licensed under other. derived from SC117/QwenPaw-Flash-9B-heretic.

- **Repository**: SC117/QwenPaw-Flash-9B-heretic-mlx-8Bit
- **License**: other
- **Tasks**: text-generation
- **Parameters**: 2.5B
- **Base model**: SC117/QwenPaw-Flash-9B-heretic
- **Tags**: mlx
- **Downloads**: 134
- **Stars**: 0
- **Last updated**: 2026-10-04

Source: https://www.modelscope.ai/models/SC117/QwenPaw-Flash-9B-heretic-mlx-8Bit

---

# SC117/QwenPaw-Flash-9B-heretic-mlx-8Bit

The Model [SC117/QwenPaw-Flash-9B-heretic-mlx-8Bit](https://huggingface.co/SC117/QwenPaw-Flash-9B-heretic-mlx-8Bit) was converted to MLX format from [SC117/QwenPaw-Flash-9B-heretic](https://huggingface.co/SC117/QwenPaw-Flash-9B-heretic) using mlx-lm version **0.31.2**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("SC117/QwenPaw-Flash-9B-heretic-mlx-8Bit")

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)
```


<!-- SC117_SUPPORT_START -->
<div align="center">
  <a href="https://ko-fi.com/sc117">
    <img
      src="https://huggingface.co/SC117/Qwen3.8-Flash-Next-GSQ-RCO-abliterated-GGUF/resolve/main/assets/support-sc117.png"
      alt="Support SC117 on Ko-fi — support is optional and all releases remain freely available."
      width="100%"
    />
  </a>
</div>
<!-- SC117_SUPPORT_END -->