---
library_name: transformers
base_model: DavidAU/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL
datasets:
- TeichAI/claude-4.5-opus-high-reasoning-250x
- TeichAI/gemini-3-pro-preview-high-reasoning-250x
- TeichAI/gpt-5.2-high-reasoning-250x
language:
- en
- fr
- de
- es
- it
- pt
- ru
- zh
- ja
tags:
- thinking
- reasoning
- Gemini
- Claude Opus
- Gpt5.2
- Distill
- finetune
- creative
- creative writing
- fiction writing
- plot generation
- sub-plot generation
- story generation
- scene continue
- storytelling
- fiction story
- science fiction
- romance
- all genres
- story
- writing
- vivid prose
- vivid writing
- fiction
- roleplaying
- bfloat16
- swearing
- rp
- horror
- unsloth
- context 1 million
- mlx
- mlx-my-repo
pipeline_tag: text-generation
---

# alexgusevski/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-mlx-5Bit

The Model [alexgusevski/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-mlx-5Bit](https://huggingface.co/alexgusevski/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-mlx-5Bit) was converted to MLX format from [DavidAU/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL](https://huggingface.co/DavidAU/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL) using mlx-lm version **0.29.1**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("alexgusevski/Qwen2.5-7B-Instruct-1M-Thinking-Claude-Gemini-GPT5.2-DISTILL-mlx-5Bit")

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)
```