Instructions to use Ex0bit/Gemma4-PRISM-PRO-DQ with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ex0bit/Gemma4-PRISM-PRO-DQ with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ex0bit/Gemma4-PRISM-PRO-DQ",
	filename="Gemma4-PRISM-PRO-DQ-GGUF/gemma4-prism-pro-dq.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 Ex0bit/Gemma4-PRISM-PRO-DQ with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ex0bit/Gemma4-PRISM-PRO-DQ
# Run inference directly in the terminal:
llama-cli -hf Ex0bit/Gemma4-PRISM-PRO-DQ

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Ex0bit/Gemma4-PRISM-PRO-DQ
# Run inference directly in the terminal:
llama-cli -hf Ex0bit/Gemma4-PRISM-PRO-DQ

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 Ex0bit/Gemma4-PRISM-PRO-DQ
# Run inference directly in the terminal:
./llama-cli -hf Ex0bit/Gemma4-PRISM-PRO-DQ

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 Ex0bit/Gemma4-PRISM-PRO-DQ
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ex0bit/Gemma4-PRISM-PRO-DQ

Use Docker

docker model run hf.co/Ex0bit/Gemma4-PRISM-PRO-DQ

LM Studio
Jan

vLLM

How to use Ex0bit/Gemma4-PRISM-PRO-DQ with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ex0bit/Gemma4-PRISM-PRO-DQ"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ex0bit/Gemma4-PRISM-PRO-DQ",
		"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/Ex0bit/Gemma4-PRISM-PRO-DQ

Ollama
How to use Ex0bit/Gemma4-PRISM-PRO-DQ with Ollama:
```
ollama run hf.co/Ex0bit/Gemma4-PRISM-PRO-DQ
```

Unsloth Studio new

How to use Ex0bit/Gemma4-PRISM-PRO-DQ 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 Ex0bit/Gemma4-PRISM-PRO-DQ 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 Ex0bit/Gemma4-PRISM-PRO-DQ to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ex0bit/Gemma4-PRISM-PRO-DQ to start chatting

Pi new

How to use Ex0bit/Gemma4-PRISM-PRO-DQ with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ex0bit/Gemma4-PRISM-PRO-DQ

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": "Ex0bit/Gemma4-PRISM-PRO-DQ"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Ex0bit/Gemma4-PRISM-PRO-DQ with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Ex0bit/Gemma4-PRISM-PRO-DQ

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default Ex0bit/Gemma4-PRISM-PRO-DQ

Run Hermes

hermes

Docker Model Runner
How to use Ex0bit/Gemma4-PRISM-PRO-DQ with Docker Model Runner:
```
docker model run hf.co/Ex0bit/Gemma4-PRISM-PRO-DQ
```

Lemonade

How to use Ex0bit/Gemma4-PRISM-PRO-DQ with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ex0bit/Gemma4-PRISM-PRO-DQ

Run and chat with the model

lemonade run user.Gemma4-PRISM-PRO-DQ-{{QUANT_TAG}}

List all available models

lemonade list

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

G4-PRISM-PRO — PRISM Dynamic Quantization

Gemma 4 31B-It PRISM-PRO-Dynamic-Quant

PRISM-PRO: Production model with full over-refusal and bias mechanisms completely removed using State of the Art PRISM pipeline.
DQ: Per-tensor-class mixed-precision allocation derived entirely from weight structure sensitivity analysis - not closed-gated Datasets.

Created by Ex0bit

💡 This model is free for active members, or available for purchase to all others here: https://ko-fi.com/s/0daff0e074. Support My Research & Development efforts. Members Recieve access to the latest PRISM-PRO Model drops on Day-0

Model Details

Property	Value
Base Model	google/gemma-4-31B-it
Architecture	Gemma 4 ISWA (Interleaved Sliding Window Attention)
Parameters	31B dense
Quantization	PRISM-PRO-DYNAMIC-QUANT
Achieved BPW	5.02
File Size	~19 GB
Context Length	262,144 tokens
Modalities	Text, Image, Video, Audio
Creator	Ex0bit

Supported Modalities

Text: Full instruction-following and chat
Image: Vision understanding via SigLIP encoder (280 tokens/image)
Video: Gemma4VideoProcessor (32 frames, pooled)
Audio: 40ms per token, 750 token sequence length

PRISM-DQ Quantization

This model uses PRISM-PRO Dynamic Quantization — a proprietary per-tensor-class mixed-precision allocation that assigns different quantization types to different tensor classes based on 7 structural weight metrics.

Unlike uniform quantization (Q4_K_M, Q5_K_M), PRISM-DQ analyzes each tensor class's sensitivity to quantization error and allocates precision where it matters most. Attention projections receive higher precision than FFN layers, with block-level overrides that protect early layers (high downstream error propagation).

No calibration data, no importance matrices, no training data required.

The result: BF16-equivalent quality at 5.02 bits-per-weight — a 68% size reduction with zero measurable quality loss.

Usage

llama.cpp

llama-server --model Gemma4-PRISM-PRO-DQ-GGUF/gemma4-prism-pro-dq.gguf \
  --port 8080 -ngl 99

LM Studio

Download the GGUF file and load it in LM Studio. The model will be detected as Gemma 4 31B.

Ollama

ollama create g4-prism -f Modelfile

Refusal & Bias Removal

This model has been treated to remove bias, over-refusals and propaganda from the base google/gemma-4-31B-it using the State of The Art PRISM pipeline.