Qwen3.5-4B-Aggressive

Instructions to use VECTORVV1/Qwen3.5-4B-Aggressive with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VECTORVV1/Qwen3.5-4B-Aggressive with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="VECTORVV1/Qwen3.5-4B-Aggressive",
	filename="Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use VECTORVV1/Qwen3.5-4B-Aggressive with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M

Use Docker

docker model run hf.co/VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M

LM Studio
Jan
Ollama
How to use VECTORVV1/Qwen3.5-4B-Aggressive with Ollama:
```
ollama run hf.co/VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M
```

Unsloth Studio new

How to use VECTORVV1/Qwen3.5-4B-Aggressive with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for VECTORVV1/Qwen3.5-4B-Aggressive to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for VECTORVV1/Qwen3.5-4B-Aggressive to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for VECTORVV1/Qwen3.5-4B-Aggressive to start chatting

Pi new

How to use VECTORVV1/Qwen3.5-4B-Aggressive with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Qwen3.5-4B-Aggressive"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use VECTORVV1/Qwen3.5-4B-Aggressive with Docker Model Runner:
```
docker model run hf.co/VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M
```

Lemonade

How to use VECTORVV1/Qwen3.5-4B-Aggressive with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VECTORVV1/Qwen3.5-4B-Aggressive:Q4_K_M

Run and chat with the model

lemonade run user.Qwen3.5-4B-Aggressive-Q4_K_M

List all available models

lemonade list

Qwen3.5-4B-Aggressive / README.md

VECTORVV1

Duplicate from HauhauCS/Qwen3.5-4B-Uncensored-HauhauCS-Aggressive

926f247 23 days ago

preview code

raw

history blame contribute delete

2.92 kB

	---
	license: apache-2.0
	tags:
	- uncensored
	- qwen3.5
	- qwen
	- gguf
	language:
	- en
	- zh
	- multilingual
	---

	# Qwen3.5-4B-Uncensored-HauhauCS-Aggressive

	> [Join the Discord](https://discord.gg/SZ5vacTXYf) for updates, roadmaps, projects, or just to chat.

	Qwen3.5-4B uncensored by HauhauCS.

	## About

	0/465 refusals. Fully uncensored with zero capability loss.

	No changes to datasets or capabilities. Fully functional, 100% of what the original authors intended - just without the refusals.

	These are meant to be the best lossless uncensored models out there.

	## Aggressive Variant

	Stronger uncensoring with more thorough refusal removal. If this variant is too loose for your use case, a Balanced variant may follow.

	Note: The model is fully unlocked and will not refuse prompts. However, it may occasionally append a short disclaimer at the end of a response (e.g. "This is general information, not legal advice..."). This is baked into the base model's training and not a refusal — the actual content is still generated in full.

	## Downloads

	\| File \| Quant \| Size \|
	\|------\|-------\|------\|
	\| Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf \| BF16 \| 7.9 GB \|
	\| Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q8_0.gguf \| Q8_0 \| 4.2 GB \|
	\| Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf \| Q6_K \| 3.3 GB \|
	\| Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \| Q4_K_M \| 2.6 GB \|
	\| mmproj-Qwen3.5-4B-Uncensored-HauhauCS-Aggressive-BF16.gguf \| Vision encoder \| 645 MB \|

	Vision support: This model is natively multimodal. The `mmproj` file is the vision encoder — you need it alongside the main GGUF to use image/video inputs. Load both files in llama.cpp, LM Studio, or any compatible runtime.

	## Specs

	- 4B dense parameters, 32 layers
	- Hybrid architecture: Gated DeltaNet linear attention + full softmax attention (3:1 ratio)
	- 262K native context (extendable to 1M with YaRN)
	- Natively multimodal (text, image, video)
	- Multi-token prediction (MTP) support
	- 248K vocabulary, 201 languages
	- Based on [Qwen3.5-4B](https://huggingface.co/Qwen/Qwen3.5-4B)

	## Recommended Settings

	From the official Qwen authors:

	Thinking mode (default):
	- `temperature=0.6`, `top_p=0.95`, `top_k=20`, `min_p=0`

	Non-thinking mode:
	- `temperature=0.7`, `top_p=0.8`, `top_k=20`, `min_p=0`

	Important:
	- Maintain at least 128K context to preserve thinking capabilities
	- For production/high-throughput: use vLLM, SGLang, or KTransformers

	Note: This is a brand new architecture (released 2026-03-02). llama.cpp support landed very recently — make sure you're on a recent build. Works with llama.cpp, LM Studio, Jan, koboldcpp, etc.

	Also check out the [9B variant](https://huggingface.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive) and all releases at [HauhauCS](https://huggingface.co/HauhauCS).

	## Usage

	Works with llama.cpp, LM Studio, Jan, koboldcpp, etc.