MiMo-V2.6-Flash-RL-mxfp4-q8

mlx-community/MiMo-V2.6-Flash-RL-mxfp4-q8#

This model mlx-community/MiMo-V2.6-Flash-RL-mxfp4-q8 was converted to MLX format from XiaomiMiMo/MiMo-V2.6-Flash-RL using mlx-lm version 0.32.0 (PR #1219).

Quantization#

• MoE expert weights are the original checkpoint's native MXFP4 (4-bit, group size 32), loaded directly without requantization.
• Attention, dense MLP, embeddings and lm_head are 8-bit affine, group size 64.
• 4.334 bits per weight overall, 156 GB on disk. Loading takes about 170 GB of unified memory.

This is a text-only conversion: the vision and audio encoders and the MTP/DFlash draft weights are not included.

Requirements#

MiMo-V2 support is in mlx-lm PR #1219. Until it is merged, install mlx-lm from that branch:

pip install git+https://github.com/kernelpool/mlx-lm.git@add-mimo-v2

Use with mlx#

from mlx_lm import load, generate

model, tokenizer = load("mlx-community/MiMo-V2.6-Flash-RL-mxfp4-q8")

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)

Thinking is enabled by default in the chat template; pass enable_thinking=False to apply_chat_template to disable it. Tool calls use the Qwen3-Coder format (<tool_call><function=...>), which the qwen3_coder tool parser in mlx-lm handles.