---
license: apache-2.0
library_name: transformers
pipeline_tag: image-text-to-text
base_model: DJLougen/Qwable-5-27B-Coder
base_model_relation: finetune
language:
- en
tags:
- transformers
- safetensors
- qwen
- qwen3_6
- qwen3_5
- coder
- coding-agent
- agentic-coding
- tool-use
- function-calling
- repository-work
- terminal-workflows
- long-context
- image-text-to-text
- text-generation-inference
- unsloth
- trl
- mlx
- mlx-my-repo
---

# porschefreak/Qwable-5-27B-Coder-mlx-4Bit

The Model [porschefreak/Qwable-5-27B-Coder-mlx-4Bit](https://huggingface.co/porschefreak/Qwable-5-27B-Coder-mlx-4Bit) was converted to MLX format from [DJLougen/Qwable-5-27B-Coder](https://huggingface.co/DJLougen/Qwable-5-27B-Coder) 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("porschefreak/Qwable-5-27B-Coder-mlx-4Bit")

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)
```