mlx-community/MiniMax-M3.1-Flash-Text-4bit

This model mlx-community/MiniMax-M3.1-Flash-Text-4bit 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 weights keep the original quantization. The routed experts are NVFP4 with a per-expert global scale, the attention, shared expert and dense MLP layers are MXFP8, and the router stays in float32. Greedy output matched the original checkpoint token for token in testing. Peak memory was about 249 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-4bit")

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)