Skip to content
Video

10Eros Max INT8 ref2va

турбо-чекпоинт для видео-референсов на MiniMax H3

1 min read

Комьюнити-квантование INT8 от Stuubzzz: 10Eros_Max beta2 на базе MiniMax H3 ref2va. Это чекпоинт для reference-to-video-audio в ComfyUI, ориентированный на видео-референсы и быстрый multi-video reference; весит меньше трети bf16-версии.

Ключевые особенности

  • INT8 ConvRot: менее трети размера bf16.
  • Drop-in для стандартных H3 ref2va workflow: те же загрузчики и нативные int8-ядра, без LoRA-нод и кастомных нод.
  • Заточен под видео-референсы и быстрый multi-video reference.
  • Для чисто image reference автор базовой работы рекомендует FL-модель TenStrip — она лучше подходит.
  • Ранний экспериментальный turbo-merge, не финальный релиз.
  • Нужен стандартный стек H3: H3-truncated Qwen3-VL, видео- и аудио-VAE MiniMax и свежий ComfyUI с comfy_quant int8_convrot.

Пример

Сценарий из карточки: подключите чекпоинт вместо официального int8 ref2va в обычный H3 ref2va workflow ComfyUI и подайте видео-референс. Промпт строится по официальному шестисекционному Full-Reference формату из ref-mode prompt guide репозитория MiniMax-H3.

ПодробнееКвантование: TensorWiseINT8Layout convrot, group-wise Hadamard rotation, groupsize 256; 100% элементов в пределах ±1 шага квантования относительно официального ref2va int8; конфиги comfy_quant и неизменённые тензоры байт-в-байт совпадают с официальным int8-релизом.
Размер: менее трети bf16.
Железо/стек: стандартный H3-стек — H3-truncated Qwen3-VL, MiniMax video + audio VAEs и ComfyUI с нативной загрузкой comfy_quant int8_convrot.
Ограничения: ранний экспериментальный turbo-merge; для image reference лучше FL-модель. Лицензия — MiniMax H3 Community License Agreement.
Видео-пример
Discuss 219 5.6K

Will it run?

Runs in FP8 / INT8

Full precision does not fit, a quantised version does: quality barely changes down to 8 bits, more noticeably at 4 bits.

  • BF16weights 20 GB · ready files25 GB
  • FP8 / INT8recommendedweights 9.8 GB14 GB
  • 4-bitweights 5.5 GB9.3 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 5080 · BF16 — from RTX 5090

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

A ready script for the machine we advise above: paste it and the model downloads and starts.

  1. 1. Rent RTX A6000

    $0.43 an hour with the coupon. Pick the Ubuntu image when you create the machine.

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    #!/usr/bin/env bash
    # 2868392-10eros-max-int8-ref2va-beta2
    set -e
    # ===== Tokens: paste yours between the quotes =====
    export CIVITAI_TOKEN=""   # civitai.com/user/account → API Keys, for Civitai LoRAs
    # ==========================================
    # NVIDIA driver: CUDA 13 needs 580+. If older or missing, the current nvidia-open is installed (keep yours: KEEP_DRIVER=1)
    DRV=$(nvidia-smi --query-gpu=driver_version --format=csv,noheader 2>/dev/null | head -1 | cut -d. -f1)
    case "$DRV" in ""|*[!0-9]*) DRV=0 ;; esac
    if [ "$DRV" -lt 580 ] && [ -z "${KEEP_DRIVER:-}" ]; then
      . /etc/os-release && \
      curl -fsSLO "https://developer.download.nvidia.com/compute/cuda/repos/ubuntu${VERSION_ID//./}/x86_64/cuda-keyring_1.1-1_all.deb" && \
      sudo dpkg -i cuda-keyring_1.1-1_all.deb && rm -f cuda-keyring_1.1-1_all.deb && \
      sudo apt-get update && \
      sudo DEBIAN_FRONTEND=noninteractive apt-get install -y nvidia-open || \
      { echo "Could not install the NVIDIA driver: see the error above. To keep the current one, run with KEEP_DRIVER=1."; exit 1; }
      echo "NVIDIA driver updated. Reboot the machine (sudo reboot) and run this same script again."
      exit 0
    fi
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    # CUDA 13+ → int8_convrot (Comfy-Org's advice), else fp8_scaled
    CU=$(nvidia-smi | grep -oP 'CUDA Version: \K[0-9]+' || echo 12)
    [ "$CU" -ge 13 ] && TORCH=cu130 || TORCH=cu128
    [ -d ~/ComfyUI ] || git clone https://github.com/comfyanonymous/ComfyUI ~/ComfyUI
    cd ~/ComfyUI
    uv venv --python 3.12 --allow-existing && source .venv/bin/activate
    uv pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/$TORCH
    uv pip install -r requirements.txt "huggingface_hub[cli]"
    civitai() {  # civitai <model id> <folder>: the newest version of a Civitai model
      vid=$(curl -fsSL "https://civitai.com/api/v1/models/$1" | python3 -c 'import json,sys;print(json.load(sys.stdin)["modelVersions"][0]["id"])')
      (cd "$2" && curl -fL -OJ -H "Authorization: Bearer $CIVITAI_TOKEN" "https://civitai.com/api/download/models/$vid")
    }
    # Base files: MiniMax H3, 8-bit
    if [ "$CU" -ge 13 ]; then
      hf download Comfy-Org/MiniMax-H3 text_encoders/qwen3vl_32b_minimax_h3_int8_convrot.safetensors vae/minimax_h3_video_vae_fp16.safetensors vae/minimax_h3_audio_vae_fp32.safetensors --local-dir models
    else
      hf download Comfy-Org/MiniMax-H3 text_encoders/qwen3vl_32b_minimax_h3_nvfp4_awq.safetensors vae/minimax_h3_video_vae_fp16.safetensors vae/minimax_h3_audio_vae_fp32.safetensors --local-dir models
    fi
    # Main model: 2868392-10eros-max-int8-ref2va-beta2
    civitai 2868392 models/diffusion_models
    # Start ComfyUI. From your computer: ssh -L 8188:localhost:8188 user@IP, then http://localhost:8188
    python main.py --listen 127.0.0.1 --port 8188
  3. 3. Use it

    From your computer: ssh -L 8188:localhost:8188 user@machine-IP, then open http://localhost:8188. Or open that address in the browser on the machine's desktop. The model's workflow is usually in its Hugging Face card.

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • SageAttention 3v2.2.0from October 28, 2025

    even faster on RTX 50 / Blackwell

    FP4 attention for Blackwell. Faster than SageAttention 2, but the authors suggest v2 when accuracy matters.

    How to enable: Build from the sageattention3_blackwell folder of the repo; in ComfyUI via KJNodes.

    Earlier generations (2)
    • SageAttention 2++ — Quantised (INT8/FP8) attention with no visible quality loss. The main speed-up for image and video generation.
    • SageAttention 1 — First version: INT8 for Q·K. Still works, but 2++ is faster and more accurate.
  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (3)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
    • xFormers — The older way to speed up attention, works almost everywhere. Sage or Flash are faster where available.
  • cache-dit (DBCache)v1.5.6from November 20, 2026new release

    1.5–3× at nearly the same quality

    Reuses block outputs between diffusion steps. Supports most DiT models.

    How to enable: pip install cache-dit; one line cache_dit.enable_cache(pipe) for diffusers.

    Earlier generations (2)
    • MagCache — Skips steps by magnitude of change. More accurate than TeaCache, no calibration.
    • TeaCache — The first popular diffusion step cache. Works, newer methods are more accurate.
  • LightX2V step distill0.6.1from November 9, 2026new release

    5–10× fewer steps

    Distilled LoRAs and an engine: video in 4–8 steps instead of 30–50.

    How to enable: Load their step-distill LoRA, CFG 1.0, 4–8 steps.

  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

MiniMax H3 prompts

All prompts

Ready prompts with the resulting video: copy and try.

Model family

New posts about versions of MiniMax-H3 (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 12All on Hugging Face
Merges 3All on Hugging Face

About the model

civitai/2868392-10eros-max-int8-ref2va-beta2
Author
Stuubzzz
Category
Video
Released
Posted

On NeyroLearn

Civitai

5.6K219

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments