Instructions to use KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I
# Run inference directly in the terminal:
llama cli -hf KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I
# Run inference directly in the terminal:
llama cli -hf KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

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 KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I
# Run inference directly in the terminal:
./llama-cli -hf KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

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 KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

Use Docker

docker model run hf.co/KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

LM Studio
Jan

vLLM

How to use KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

Ollama
How to use KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I with Ollama:
```
ollama run hf.co/KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I
```
Unsloth Desktop

How to use KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I with Docker Model Runner:
```
docker model run hf.co/KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I
```

Lemonade

How to use KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

Run and chat with the model

lemonade run user.Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I-{{QUANT_TAG}}

List all available models

lemonade list

Hermes Agent

How to use KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

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 KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Gemma 4 26B A4B Moonlight Dusk Heretic — PRISM-PRO-DQ Map Reapplication

Moonlight Dusk Heretic finetune converted to GGUF and quantized with an unofficial reapplication of the PRISM-PRO-DQ per-tensor type map.

Important provenance notice

This is not an official PRISM-DQ or PRISM-PRO-DQ model. This repository is not affiliated with Ex0bit, PRISM-DQ, or the authors of the source finetune.

The underlying trained weights come from Vortex5/G4-Moonlight-Dusk-26B-A4B-heretic. No trained tensor values from Ex0bit's PRISM model were copied, merged, or transplanted into this model.

The quantized file was produced by reconstructing the per-tensor GGML quantization-type assignment visible in the public Ex0bit/Gemma4-26B-A4B-PRISM-PRO-DQ-GGUF release and then applying that assignment to this separate finetune. This is therefore a map reapplication, not a reproduction of the original PRISM-DQ calibration, optimization procedure, dataset, or proprietary pipeline.

The Unsloth importance matrix imatrix_unsloth.gguf_file was used during quantization. Conversion and quantization were performed with llama.cpp.

Quantization layout

For the 658 tensors shared with the reference Gemma 4 PRISM-PRO-DQ GGUF, the final distribution is:

GGML type	Tensor count
F32	392
Q5_1	30
Q5_K	91
Q6_K	115
Q8_0	30

This source checkpoint contains a separate output.weight, resulting in 659 tensors. That tensor was preserved and stored as Q5_K rather than discarded or tied during conversion.

Files and integrity

File	Size	SHA-256	Purpose
`Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I.gguf`	17.32 GiB	`7f556d9679961ddd25c2e51ed705e6152d8a395d97cdc013d7ada2fa8447ebc3`	Unofficial PRISM-PRO-DQ tensor-map reapplication with Unsloth I-matrix

Template and tokenizer

The tokenizer vocabulary and special-token IDs were checked against the source Hugging Face tokenizer.
The embedded chat template was updated to the current official template from google/gemma-4-26B-A4B-it at conversion time.

Usage with llama.cpp

llama-cli -m Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I.gguf --jinja -p "Hello"

For server use:

llama-server -m Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I.gguf --jinja --host 127.0.0.1 --port 8080

References

Source finetune: Vortex5/G4-Moonlight-Dusk-26B-A4B-heretic
Official Gemma 4 base: google/gemma-4-26B-A4B-it
PRISM-PRO-DQ public GGUF used only as the tensor-map reference: Ex0bit/Gemma4-26B-A4B-PRISM-PRO-DQ-GGUF
Unsloth importance matrix: imatrix_unsloth.gguf_file
GGUF conversion and quantization tooling: ggml-org/llama.cpp
Gemma Terms of Use: https://ai.google.dev/gemma/terms

License and responsibility

Use of this repository remains subject to the original source model's license and the Gemma Terms of Use. The behavior and safety characteristics of the source finetune are inherited; quantization does not make the model safer or change its intended-use restrictions. Users are responsible for evaluating outputs and complying with applicable laws and licenses.

Downloads last month: 51

GGUF

Model size

26B params

Architecture

gemma4

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Model tree for KaviarLabs/Gemma-4-26B-A4B-Moonlight-Dusk-Heretic-PRISM-DQ-I

Base model

Vortex5/G4-Moonlight-Dusk-26B-A4B

Finetuned

Vortex5/G4-Moonlight-Dusk-26B-A4B-heretic

Quantized

(3)

this model