mlx-community/MiniMax-M3.1-Flash-Text-3bit

This model mlx-community/MiniMax-M3.1-Flash-Text-3bit was converted to MLX format from MiniMaxAI/MiniMax-M3.1-Flash using mlx-lm with ml-explore/mlx-lm#2003. Refer to the original model card for more details on the model.

This is a text-only conversion. The vision tower is not included.

The original weights were dequantized and then quantized to 3-bit affine with group size 64 (3.5 bits per weight). The router is kept at 8 bits. Peak memory was about 187 GB in a short generation test.

Tested with mlx-lm 0.32.2.

Use with mlx

pip install -U mlx-lm

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/MiniMax-M3.1-Flash-Text-3bit")

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)