---
license: apache-2.0
language:
- en
base_model: SicariusSicariiStuff/Impish_Nemo_12B
datasets:
- SicariusSicariiStuff/UBW_Tapestries
widget:
- text: Impish_Nemo_12B
  output:
    url: https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B/resolve/main/Images/Impish_Nemo_12B.png
tags:
- mlx
---

# alexgusevski/Impish_Nemo_12B-mlx-2Bit

The Model [alexgusevski/Impish_Nemo_12B-mlx-2Bit](https://huggingface.co/alexgusevski/Impish_Nemo_12B-mlx-2Bit) was converted to MLX format from [SicariusSicariiStuff/Impish_Nemo_12B](https://huggingface.co/SicariusSicariiStuff/Impish_Nemo_12B) 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/Impish_Nemo_12B-mlx-2Bit")

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)
```