---

library_name: llama.cpp

license: apache-2.0

language:

- en

- zh

pipeline_tag: image-text-to-text

base_model: wesjos/Qwen3.5-4B-Fuck

tags:

- gguf

- qwen3_5

- conversational

---

Qwen3.5-4B-Fuck — GGUF

GGUF builds of wesjos/Qwen3.5-4B-Fuck — a Qwen3.5-4B fine-tune that answers correctly and insults you while doing it.

> [!WARNING]

> Profanity and personal attacks by design, EN + 中文. Not for customer-facing use, not for anyone who has not opted in. 18+ / research & entertainment.

Files

| File | Size | Notes |

|---|---|---|

| Qwen3.5-4B-Fuck-Q4_K_M.gguf | 2.52 GiB | default; the one in the screenshots |

| Qwen3.5-4B-Fuck-Q8_0.gguf | 4.17 GiB | near-lossless |

| mmproj-Qwen3.5-4B-BF16.gguf | 644 MiB | vision projector — only for image / video input |

The bf16 safetensors shards are mirrored here as well (8.68 GiB) if you want the transformers format instead of GGUF. Otherwise ignore them.

Demo

<a href="https://huggingface.co/wesjos/Qwen3.5-4B-Fuck-GGUF/blob/main/demo-full/demo-en-full.png"><img src="demo/demo-en.png" width="772"></a>

_{<b>EN</b> · <code>what is 8.2x9.12/2.3</code> — right answer, wrong manners · <a href="https://huggingface.co/wesjos/Qwen3.5-4B-Fuck-GGUF/blob/main/demo-full/demo-en-full.png">click to enlarge</a>}

<br>

<a href="https://huggingface.co/wesjos/Qwen3.5-4B-Fuck-GGUF/blob/main/demo-full/demo-zh-full.png"><img src="demo/demo-zh.png" width="772"></a>

_{<b>中文</b> · <code>python是什么意思</code> — 问一句被骂一段 · <a href="https://huggingface.co/wesjos/Qwen3.5-4B-Fuck-GGUF/blob/main/demo-full/demo-zh-full.png">点击放大</a>}

_{Thumbnails are cropped tight to the chat pane; tap either one for the full-resolution capture.}

Run it

hf download wesjos/Qwen3.5-4B-Fuck-GGUF \
  Qwen3.5-4B-Fuck-Q4_K_M.gguf mmproj-Qwen3.5-4B-BF16.gguf --local-dir .

# OpenAI-compatible server on http://localhost:8080
llama-server -m Qwen3.5-4B-Fuck-Q4_K_M.gguf \
  --mmproj mmproj-Qwen3.5-4B-BF16.gguf \
  -c 32768 -ngl 99 --jinja --port 8080

# terminal chat, no server
llama-cli -m Qwen3.5-4B-Fuck-Q4_K_M.gguf -cnv -c 8192 -ngl 99 --jinja \
  --temp 0.85 --top-p 0.95 --top-k 20 --presence-penalty 1.5

Text only? Drop --mmproj and skip that file — saves 644 MiB.

Sampling

What the demos ran with:

| temperature | top_p | top_k | min_p | presence_penalty | repetition_penalty |

|---|---|---|---|---|---|

| 0.85 | 0.95 | 20 | — | 1.5 | off |

Notes

• Qwen3.5 thinks before answering by default — llama.cpp will print the reasoning before the answer, the screenshots show only the answer.
• Rudeness is baked into the weights; refusals are inherited from the base and were not audited. Not an "uncensored" model.
• Q4_K_M is the safe default for an 8 GB card (weights 2.52 GiB + 32K context fits comfortably); 16 GB and up can take Q8_0.
• Demo screenshots are LM Studio. The settings sidebar, the empty left gutter, and the input box were cropped away; the model name, every line of dialogue and the 100.7 tok/s throughput readout are as captured.

中文说明

GGUF 量化版，看上面表格。Q4_K_M 约 2.5 GiB，8 GB 显存跑 32K 上下文很宽松。--mmproj 是视觉投影，只用文本就别带。

嘴臭是训练出来的，不是提示词装的。请勿用于客服或任何没同意被骂的人。

License

Apache-2.0, inherited from Qwen3.5-4B via wesjos/Qwen3.5-4B-Fuck.