---
license: apache-2.0
datasets:
- nvidia/OpenCodeReasoning
- vicgalle/creative-rubrics-gpt-4.5-o3-R1
base_model: DavidAU/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x
language:
- en
pipeline_tag: text-generation
tags:
- merge
- programming
- code generation
- code
- coding
- coder
- chat
- brainstorm
- qwen
- qwen3
- qwencoder
- brainstorm20x
- unsloth
- trl
- sft
- cot
- reasoning
- thinking
- think
- mlx
library_name: mlx
---

# Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-q8-mlx

This model [Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-q8-mlx](https://huggingface.co/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-q8-mlx) was
converted to MLX format from [DavidAU/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x](https://huggingface.co/DavidAU/Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x)
using mlx-lm version **0.26.0**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Qwen3-Code-Reasoning-Instruct-6B-Brainstorm20x-q8-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
    )

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