---
license: other
license_name: modified-mit
library_name: transformers
base_model: moonshotai/Kimi-K2-Instruct-0905
tags:
- mlx
---

# cs2764/Kimi-K2-Instruct-0905-mlx-mixed_2_6

The Model [cs2764/Kimi-K2-Instruct-0905-mlx-mixed_2_6](https://huggingface.co/cs2764/Kimi-K2-Instruct-0905-mlx-mixed_2_6) was converted to MLX format from [moonshotai/Kimi-K2-Instruct-0905](https://huggingface.co/moonshotai/Kimi-K2-Instruct-0905) using mlx-lm version **0.28.0**.

## Quantization Details

This model was converted with the following quantization settings:

- **Quantization Strategy**: mixed_2_6 (Mixed precision)
- **Average bits per weight**: 3.146

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("cs2764/Kimi-K2-Instruct-0905-mlx-mixed_2_6")

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)
```