README.md

metadata

base_model:
  - anthracite-core/Mistral-Small-3.1-24B-Instruct-2503-HF
license: mit
pipeline_tag: text-generation

mlx-community/Mistral-Small-3.1-24B-Instruct-TXT-2503-3bit-AWQ

This model mlx-community/Mistral-Small-3.1-24B-Instruct-TXT-2503-3bit-AWQ was converted to MLX format from anthracite-core/Mistral-Small-3.1-24B-Instruct-2503-HF using mlx-lm version 0.24.1.

Use with mlx

pip install mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/Mistral-Small-3.1-24B-Instruct-TXT-2503-3bit-AWQ")

prompt = "hello"

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

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