Skip to content
Video

Qwen-Rapid-NSFW-v18 Q6_K

GGUF-веса text-to-video на базе WAN2.2

1 min read

Репозиторий RunningHubAI с квантованными весами GGUF для генерации видео из текста. Единственный файл Qwen-Rapid-NSFW-v18_Q6_K.gguf занимает 16 207 MiB; модель — файнтюн от WAN2.2. Веса рассчитаны на загрузку в ComfyUI, RunningHub или Hugging Face.

Ключевые особенности

  • Формат GGUF, квантование Q6_K — один файл весов без отдельного конфига.
  • База — WAN2.2, задача text-to-video.
  • Размер файла 16 207 MiB (≈15,8 GiB) — ориентир по памяти при загрузке.
  • Оригинальный проект и автор опубликованы на RunningHub.
  • Бенчмарков, требований к VRAM и деталей обучения в карточке нет.

Пример

Сценарий: загрузите Qwen-Rapid-NSFW-v18_Q6_K.gguf в ComfyUI (или RunningHub) и подайте текстовый промпт, например: slow camera pan over a rainy neon street at night, cinematic lighting. Карточка не содержит кода запуска — используется штатный workflow выбранной платформы.

ПодробнееФайл: Qwen-Rapid-NSFW-v18_Q6_K.gguf, 16 207 MiB, квант Q6_K.
База: файнтюн от WAN2.2.
Платформы: ComfyUI / RunningHub / Hugging Face.
Лицензия: по исходному проекту или upstream, копирайт остаётся у автора.
Бенчмарки и требования к железу не указаны.
Discuss Telegram 0 82

Will it run?

Runs in GGUF Q6_K

The most precise of the ready quantised files fits.

  • GGUF Q6_Kweights 16 GB · ready files21 GB

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: GGUF Q6_K — from RTX 4090

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

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    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.

    # RunningHubAI/rh-qwen-rapid-nsfw-v18-q6-k.gguf-gguf
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download RunningHubAI/rh-qwen-rapid-nsfw-v18-q6-k.gguf-gguf --local-dir ~/models/rh-qwen-rapid-nsfw-v18-q6-k.gguf-gguf
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

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.

Model family

New posts about versions of rh-qwen-rapid-nsfw-v18-q6-k.gguf-gguf (quants, finetunes, LoRAs) will show up under the bell.

No known relatives of this model yet. All derivatives on Hugging Face

About the model

RunningHubAI/rh-qwen-rapid-nsfw-v18-q6-k.gguf-gguf
Author
RunningHubAI
Category
Video
Released
Posted

On NeyroLearn

Hugging Face

820

Ask AI about this model

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

Comments

Language models

parchi-v3

parchi-v3