Gemma-4-E4B-Aggressive

Instructions to use VECTORVV1/Gemma-4-E4B-Aggressive with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use VECTORVV1/Gemma-4-E4B-Aggressive with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="VECTORVV1/Gemma-4-E4B-Aggressive",
	filename="Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": [
				{
					"type": "text",
					"text": "Describe this image in one sentence."
				},
				{
					"type": "image_url",
					"image_url": {
						"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
					}
				}
			]
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use VECTORVV1/Gemma-4-E4B-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/Gemma-4-E4B-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf VECTORVV1/Gemma-4-E4B-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/Gemma-4-E4B-Aggressive:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf VECTORVV1/Gemma-4-E4B-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/Gemma-4-E4B-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf VECTORVV1/Gemma-4-E4B-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/Gemma-4-E4B-Aggressive:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf VECTORVV1/Gemma-4-E4B-Aggressive:Q4_K_M

Use Docker

docker model run hf.co/VECTORVV1/Gemma-4-E4B-Aggressive:Q4_K_M

LM Studio
Jan

vLLM

How to use VECTORVV1/Gemma-4-E4B-Aggressive with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "VECTORVV1/Gemma-4-E4B-Aggressive"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "VECTORVV1/Gemma-4-E4B-Aggressive",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/VECTORVV1/Gemma-4-E4B-Aggressive:Q4_K_M

Ollama
How to use VECTORVV1/Gemma-4-E4B-Aggressive with Ollama:
```
ollama run hf.co/VECTORVV1/Gemma-4-E4B-Aggressive:Q4_K_M
```

Unsloth Studio new

How to use VECTORVV1/Gemma-4-E4B-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/Gemma-4-E4B-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/Gemma-4-E4B-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/Gemma-4-E4B-Aggressive to start chatting

Pi new

How to use VECTORVV1/Gemma-4-E4B-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/Gemma-4-E4B-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": "Gemma-4-E4B-Aggressive"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use VECTORVV1/Gemma-4-E4B-Aggressive with Docker Model Runner:
```
docker model run hf.co/VECTORVV1/Gemma-4-E4B-Aggressive:Q4_K_M
```

Lemonade

How to use VECTORVV1/Gemma-4-E4B-Aggressive with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull VECTORVV1/Gemma-4-E4B-Aggressive:Q4_K_M

Run and chat with the model

lemonade run user.Gemma-4-E4B-Aggressive-Q4_K_M

List all available models

lemonade list

VECTORVV1

HauhauCS commited on 23 days ago

Commit

9ebf7a0

0 Parent(s):

Duplicate from HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive

Browse files

Co-authored-by: HauHau <HauhauCS@users.noreply.huggingface.co>

Files changed (14) hide show

.gitattributes +47 -0
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf +3 -0
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf +3 -0
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf +3 -0
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_M.gguf +3 -0
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf +3 -0
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf +3 -0
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf +3 -0
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_M.gguf +3 -0
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf +3 -0
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf +3 -0
Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf +3 -0
README.md +103 -0
mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf +3 -0

.gitattributes ADDED Viewed

	@@ -0,0 +1,47 @@

+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf filter=lfs diff=lfs merge=lfs -text

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d17a59387ef0ada0823fb4572b609da920d822f31b6ac983e323da55c31aa3a2
+size 4714690528

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8e533ca658a3959fd3ee8b5f575c24b87c5a278649d5053480d4cce280bdbd6c
+size 5070950368

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:1292d4767733de9e182a9bfd274d371103f0695cc0ca1f5f6678e5a855942d42
+size 4431882208

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a60db97bb4f61f0167d64f369c198428b2bb10a636b6f339f2f947ac40202a98
+size 4850391008

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:15636005886b262a5920cbdae8b9881b2a6bb5c1dadc4784ec3c89acf498571c
+size 4884505568

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:d0027dd3a9128d9323e9f282c8bf010a8526c46477584535991dc1a869b56e96
+size 5335285728

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:05146429870f4ec4c16882f44bec29c51e4797463ad7080044a5c748cabb2486
+size 5369246688

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_M.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:c96f1afc2af92bb27b1d5057fd91c8f6e41e9a72f9f32faa389e1601a6963ee6
+size 5762908128

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:be18995dc554b6509254f38fd7d6f3193793091750072a57af47bca2525b1521
+size 5812940768

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f28b0ae262158af10d847c3f01bfdb943161dd31320f3aed20775ee2ad6c67a6
+size 6249794528

Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a4c4177f9fd7e3f56522675afb742f079a53f9226195b7db5e9888c872f053da
+size 8133226464

README.md ADDED Viewed

	@@ -0,0 +1,103 @@

+---
+license: gemma
+tags:
+  - uncensored
+  - gemma4
+  - abliterated
+  - gguf
+  - vision
+  - multimodal
+  - audio
+language:
+  - en
+  - multilingual
+pipeline_tag: image-text-to-text
+base_model: google/gemma-4-e4b-it
+---
+# Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
+> **[Join the Discord](https://discord.gg/SZ5vacTXYf)** for updates, roadmaps, projects, or just to chat.
+Gemma 4 E4B-IT uncensored by HauhauCS. **0/465 Refusals\***
+> **HuggingFace's "Hardware Compatibility" widget doesn't recognize K_P quants** — it may show fewer files than actually exist. Click **"View +X variants"** or go to **Files and versions** to see all available downloads.
+## About
+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 — model is fully unlocked and won't refuse prompts. May occasionally append short disclaimers (baked into base model training, not refusals) but full content is always generated.
+For a more conservative uncensor that keeps some safety guardrails, check the Balanced variant when it's available.
+## Downloads
+| File | Quant | BPW | Size |
+|------|-------|-----|------|
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q8_K_P.gguf) | Q8_K_P | 9.4 | 7.6 GB |
+| — | Q8_0 | 8.5 | — |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q6_K_P.gguf) | Q6_K_P | 7.0 | 5.9 GB |
+| — | Q6_K | 6.6 | — |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_P.gguf) | Q5_K_P | 6.1 | 5.5 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_M.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q5_K_M.gguf) | Q5_K_M | 5.7 | 5.4 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_P.gguf) | Q4_K_P | 5.2 | 5.1 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf) | Q4_K_M | 4.8 | 5.0 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ4_XS.gguf) | IQ4_XS | 4.3 | 4.8 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_P.gguf) | Q3_K_P | 4.1 | 4.6 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_M.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q3_K_M.gguf) | Q3_K_M | 3.9 | 4.6 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-IQ3_M.gguf) | IQ3_M | 3.7 | 4.4 GB |
+| [Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q2_K_P.gguf) | Q2_K_P | 3.5 | 4.2 GB |
+| [mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf](https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive/resolve/main/mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf) | mmproj (f16) | — | 945 MB |
+All quants generated with importance matrix (imatrix) for optimal quality preservation on abliterated weights.
+## What are K_P quants?
+K_P ("Perfect") quants are HauhauCS custom quantizations that use model-specific analysis to selectively preserve quality where it matters most. Each model gets its own optimized quantization profile.
+A K_P quant effectively bumps quality up by 1-2 quant levels at only ~5-15% larger file size than the base quant. Fully compatible with llama.cpp, LM Studio, and any GGUF-compatible runtime — no special builds needed.
+**Note:** K_P quants may show as "?" in LM Studio's quant column. This is a display issue only — the model loads and runs fine.
+## Specs
+- 4B parameters
+- 42 layers, mixed sliding window (512) + full attention
+- 131K context
+- Natively multimodal (text, image, video, audio)
+- 18 KV shared layers for memory efficiency
+- Based on [google/gemma-4-e4b-it](https://huggingface.co/google/gemma-4-e4b-it)
+## Recommended Settings
+From the official Google Gemma 4 authors:
+- `temperature=1.0, top_p=0.95, top_k=64`
+**Important:**
+- Use `--jinja` flag with llama.cpp for proper chat template handling
+- Vision/audio support requires the `mmproj` file alongside the main GGUF
+## Usage
+Works with llama.cpp, LM Studio, Jan, koboldcpp, and other GGUF-compatible runtimes.
+```bash
+# Text only
+llama-cli -m Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \
+  --jinja -c 8192 -ngl 99
+# With vision/audio
+llama-cli -m Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-Q4_K_M.gguf \
+  --mmproj mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf \
+  --jinja -c 8192 -ngl 99
+```
+---
+**\*** Gemma 4 didn't get as much manual testing time at longer context as my other releases. Google is now using techniques similar to NVIDIA's GenRM — generative reward models that act as internal critics — making (true) uncensoring an increasingly challenging field. I expect 99.999% of users won't hit edge cases, but the asterisk is there for honesty.

mmproj-Gemma-4-E4B-Uncensored-HauhauCS-Aggressive-f16.gguf ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:debad39ab9c1152ab67695a674fb35e8375b2320c57bfd5075835d3ccb16c7db
+size 990288832