gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF

Instructions to use Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF",
	filename="gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

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 Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

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 Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF with Ollama:
```
ollama run hf.co/Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
```

Unsloth Studio

How to use Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF 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 Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF 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 Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF to start chatting

How to use Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

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": "Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

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 Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
```

Lemonade

How to use Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF-Q8_0

List all available models

lemonade list

Gemma 4 26B A4B IT QAT Assistant MTP Q8_0 GGUF

This repository contains a GGUF conversion of the official Google Gemma 4 26B A4B IT QAT assistant/drafter checkpoint.

Source checkpoint: google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant
Output file: gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0.gguf
Quantization: Q8_0
Format: GGUF
Intended runtime: llama.cpp with Gemma 4 MTP / draft-model support

This is not a standalone chat model. It is an assistant / drafter / MTP head intended to be used together with a matching Gemma 4 26B A4B IT QAT target model for speculative decoding.

File

File	Description
`gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0.gguf`	Q8_0 GGUF conversion of the Gemma 4 26B A4B QAT assistant checkpoint

Source

Converted from the official Google checkpoint:

google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant

Usage

This GGUF is a draft / assistant / MTP model, not a standalone chat model. It must be loaded together with a matching Gemma 4 26B A4B IT QAT target model.

llama-server example:

llama-server \
  -m gemma-4-26B-A4B-it-qat-UD-Q4_K_XL.gguf \
  --model-draft gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0.gguf \
  --spec-type draft-mtp \
  --spec-draft-n-max 4

Conversion

Converted with llama.cpp using Gemma 4 assistant / MTP support:

python convert_hf_to_gguf.py \
  gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant \
  --outfile gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0.gguf \
  --outtype q8_0

Local testing

In local testing with a Gemma 4 26B A4B IT QAT target GGUF and upstream llama.cpp Gemma 4 MTP support, --spec-draft-n-max 4 gave a good balance of throughput and draft acceptance.

Notes

This file was created to make the official QAT assistant/drafter checkpoint usable with llama.cpp's Gemma 4 MTP / speculative decoding path.

This model is intended for users who already have a compatible Gemma 4 26B A4B IT QAT target GGUF and want to enable speculative decoding with the matching QAT assistant head.

License and terms

This model is a converted derivative of Google's official Gemma 4 QAT assistant checkpoint.

Gemma 4 is released under the Apache 2.0 license. Users should also review the original Google model page and comply with any applicable terms associated with the source checkpoint:

google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant

Downloads last month: 1,965

GGUF

Model size

0.4B params

Architecture

gemma4-assistant

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Janvitos/gemma-4-26B-A4B-it-qat-assistant-MTP-Q8_0-GGUF

Base model

google/gemma-4-26B-A4B-it-assistant

Finetuned

google/gemma-4-26B-A4B-it-qat-q4_0-unquantized-assistant

Quantized

(13)

this model