Modelpublic

DQN-Labs/ministral-3-3B-it2512-mlx-quantized

sourceHugging Faceapache-2.0updated 7mo agoView on Hugging Face

0likes14downloads

Model Card

DQN-Labs/ministral-3-3B-it2512-mlx-quantized

This model DQN-Labs/ministral-3-3B-it2512-mlx-quantized was converted to MLX format from mistralai/Ministral-3-3B-Instruct-2512 using mlx-lm version 0.30.7.

Use with mlx

bash

pip install mlx-lm

python

from mlx_lm import load, generate

model, tokenizer = load("DQN-Labs/ministral-3-3B-it2512-mlx-quantized")

prompt = "hello"

if tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, add_generation_prompt=True, return_dict=False,
    )

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