Skip to content
Computer vision

Huihui-Qwen3.5-9B-abliterated

Qwen3.5-9B без отказов

1 min read

Это abliterated-версия Qwen/Qwen3.5-9B от huihui-ai: у модели удалены отказы с помощью abliteration. Реализация заявлена как crude proof-of-concept и не использует TransformerLens. Размер — 9,65 млрд параметров.

Ключевые особенности

  • Удалены отказы у базовой Qwen/Qwen3.5-9B.
  • 9,65 млрд параметров; в карточке модель описана как LLM.
  • Proof-of-concept без TransformerLens.
  • Доступна в Ollama под тегом huihui_ai/qwen3.5-abliterated:9b; нужна Ollama v0.17.7.
  • Снижена фильтрация: возможны чувствительные, спорные или неподходящие ответы.

Пример

ollama run huihui_ai/qwen3.5-abliterated:9b
ПодробнееБенчмарков в карточке нет.
Требования к VRAM не указаны; для Ollama нужна версия v0.17.7.
Ограничения: сниженная безопасная фильтрация, возможны спорные и неподходящие ответы; не рекомендуется для публичных и продакшн-сценариев.
Автор советует research, тестирование или контролируемые среды.
Discuss Telegram 0 15

Will it run?

Working out the memory needs

The bot is still collecting this model's weight sizes; the estimate will appear here in a few minutes. Meanwhile you can rent a GPU with headroom.

Massed ComputeOpen Massed Compute

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.

    # AvaSiG/qwen35-9b-ablit
    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 AvaSiG/qwen35-9b-ablit --local-dir ~/models/qwen35-9b-ablit
    # The model is in ~/models. How to run it is in the model card (link above).
    Add more LoRAs to qwen35-9b-ablit
  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.

  • 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 (2)
    • 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.
  • 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 qwen35-9b-ablit (quants, finetunes, LoRAs) will show up under the bell.

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

About the model

AvaSiG/qwen35-9b-ablit
Author
AvaSiG
Category
Computer vision
Released
Posted

On NeyroLearn

Hugging Face

150

Ask AI about this model

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

Comments