QW

ai_smell_remover v1.1

QwenGGUF by grapeotUpdated 2026-09-30
Download on Hugging Face
Parameters9.2B
Context256K
Layers33
Architectureqwen35
Smallest quant9.8 GB
Quick answer

ai_smell_remover v1.1 needs about 11.4 GB of memory at Q8_0 (a 9.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 4.4 GB.

ai_smell_remover v1.1 rewrites AI‑drafted Chinese into author voice

ai_smell_remover v1.1 is a Q8_0 GGUF model built on Qwen3.5‑9B‑Base. It rewrites AI‑generated Chinese text paragraph by paragraph into the voice of author 鸭哥. The model is a LoRA trained on 185 Chinese blog posts and 2,160 paragraphs.

Good at

  • Paragraph‑by‑paragraph rewriting
  • Author‑style voice conversion
  • Maintaining original structure and length

Limits

  • No vision support
  • Requires 11.4 GB VRAM at 8 k context
  • Only tested on Mac M3 Ultra with llama.cpp

Best for

  • Rewriting AI‑drafted Chinese articles
  • Customizing author tone
  • Post‑processing AI content

Who it’s for. Developers and writers who need to transform AI‑generated Chinese text into a specific author voice while preserving structure. The model is suitable for text‑only workflows and requires a compatible GGUF runtime.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q8_09.8 GB 11.4 GB
Too big Get file →

The only available quant is Q8_0 with a file size of 9.79 GB. It needs approximately 11.4 GB VRAM at 8 k context. For lower VRAM budgets, no other quant is provided, so the model cannot be run on less than 11.4 GB of memory.

What GPU do you need for ai_smell_remover v1.1?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: the best quant that fits is Q8_0 (9.8 GB file, about 11.4 GB in use).

Which ai_smell_remover v1.1 quant should you choose?

Q8_0 (9.8 GB) is the middle option in this repository. Close to lossless. It costs roughly twice the memory of a 4-bit file, so it suits cases where you have plenty of VRAM.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen35
Parameters9.2B
Layers33
Trained context262,144 tokens
KV cache (fp16)132 KB per token

Source

Quantized bygrapeot
FamilyQwen
Licenseapache-2.0
Downloads (HF)1,314
Last updated2026-09-30

Frequently asked questions about ai_smell_remover v1.1

How much VRAM does ai_smell_remover v1.1 need?

About 11.4 GB at Q8_0 with an 8K context window. That is the 9.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run ai_smell_remover v1.1 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 11.4 GB, so you would need a larger GPU or CPU offloading.

What is the file size of ai_smell_remover v1.1 GGUF?

It depends on the quant: Q8_0 is 9.8 GB.

What context length does ai_smell_remover v1.1 support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.1 GB at 8K and 4.4 GB at 32K.

Where can I download ai_smell_remover v1.1 GGUF?

The files are on Hugging Face in the grapeot/ai_smell_remover repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does ai_smell_remover v1.1 use?

Hugging Face lists the license as apache-2.0. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run ai_smell_remover on 8 GB VRAM?

No, the model requires about 11.4 GB VRAM at 8 k context.

Does the model support vision input?

No, it only rewrites text and has no vision capability.

What runtime is needed to run this model?

Use llama.cpp with the Q8_0 GGUF file; it has been tested on Mac M3 Ultra and supports Linux and Windows.

Other GGUFs of Qwen3.5-9B-Base

Similar models

Browse all →

More from grapeot

All by grapeot →

More Qwen models

All Qwen →

Other small models

All small models →