CivArchive
    Qwen for MiniMax H3 (QP) **Fixing** - ComfyQuant
    NSFW

    Qwen for MiniMax H3 (QP)

    • This model has been quantized from a 100GB source QP training.

    • Only 2.2GB larger for NVFP4

    • This model HAS NOT been ablierated or uncensored by traditional means and is unlike any other model available currently

    The attached .json is a workflow that speed my IT time up by 60%


    NOTE UPDATE YOUR COMFY & CUDA

    Consider using --disable-dynamic-vram

    • pytorch version: 2.13.0+cu132

    • xformers version: 0.0.35

    • ComfyUI version: 0.35.0

    • comfy-aimdo version: 0.5.5

    • comfy-kitchen version: 0.2.34

    Description

    FAQ

    Comments (8)

    GlowingGuardianGirlSep 16, 2026· 2 reactions
    CivitAI

    What's QP?
    How is it different from the normal encoder?
    Why would one use it?

    VelveraSep 16, 2026
    CivitAI

    So it’s not uncensored but nsfw?

    markfjohnsonSep 17, 2026
    CivitAI

    Interesting concept but using the linked workflow and suggested models CTD's my comfyui build. Obviously a million variables there but never had another H3 workflow do that. Replacing the encoder with the stock official NVFP 4 version gets me father along workflow before it produces the same result

    navyseng340583Sep 17, 2026
    CivitAI

    这个在nsfw方面会更有出色表现么

    voayer2003587Sep 17, 2026
    CivitAI

    It is not compatible with my ComfyUI/NVFP4 setup. My Comfy is 0.33.0-13-gb963f4ad, and PyTorch is 2.7.0+cu128.

    WinnouganSep 17, 2026
    CivitAI

    What's the benefit of this text encoder?
    Why not release it in int8, w4a8, or bf16?

    N3RDGURLSep 17, 2026
    CivitAI

    I have a weird issue. I can use it just fine for text to vid, but when I try to use a reference image the whole thing crashes.

    Hamaram888Sep 18, 2026· 1 reaction
    CivitAI

    Used your workflow and standard models and it produced a high quality result. However, prompt adherence seemed to be close to zero. Stuff just happened. Is that the intent? This was from a single starting frame, not a first/last, bypassed the second image and second image resize node.

    TextEncoder
    MiniMax H3

    Details

    Downloads
    377
    Platform
    CivitAI
    Platform Status
    Available
    Created
    9/16/2026
    Updated
    9/18/2026
    Deleted
    -

    Files

    qwenForMinimaxH3QPUpdated_comfyquant_int8.safetensors

    qwenForMinimaxH3QPUpdated_comfyquant_mxfp8.safetensors

    qwenForMinimaxH3QP_comfyquant.safetensors

    qwenForMinimaxH3QP_comfyquant.json

    Mirrors