Instructions to use Horkios/Magistral-Small-2509-mlx-4Bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Horkios/Magistral-Small-2509-mlx-4Bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Magistral-Small-2509-mlx-4Bit Horkios/Magistral-Small-2509-mlx-4Bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Horkios/Magistral-Small-2509-mlx-4Bit
The Model Horkios/Magistral-Small-2509-mlx-4Bit was converted to MLX format from unsloth/Magistral-Small-2509 using mlx-lm version 0.26.4.
Use with mlx
pip install mlx-lm
from mlx_lm import load, generate
model, tokenizer = load("Horkios/Magistral-Small-2509-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)
- Downloads last month
- 22
Model size
24B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for Horkios/Magistral-Small-2509-mlx-4Bit
Base model
mistralai/Mistral-Small-3.1-24B-Base-2503 Finetuned
mistralai/Magistral-Small-2509 Finetuned
unsloth/Magistral-Small-2509