Instructions to use cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf",
	filename="gemma-4-E4B-it-qat-assistant-bf16.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 cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf: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 cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf: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 cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M

Use Docker

docker model run hf.co/cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf with Ollama:
```
ollama run hf.co/cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M
```

Unsloth Studio

How to use cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-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 cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-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 cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf to start chatting

How to use cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf: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": "cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-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 cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M

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 cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf with Docker Model Runner:
```
docker model run hf.co/cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M
```

Lemonade

How to use cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf-Q4_K_M

List all available models

lemonade list

Gemma 4 E4B IT QAT Assistant GGUF

GGUF conversions of Google's official unquantized QAT assistant/drafter checkpoint for Gemma 4 E4B IT.

Google publishes GGUFs for the main QAT models, but the assistant/drafter checkpoint is published as unquantized QAT safetensors. This repo packages the E4B assistant as GGUF for llama.cpp speculative decoding.

Base model: google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant

These files were converted with llama.cpp commit 961e9a3e46ca4cf7e6e86cfceb5b5e32084bf5f0.

The QAT assistant GGUFs also appear to work fine with regular, non-QAT Gemma 4 E4B IT target models in llama.cpp.

Usage

llama-server \
  -m gemma-4-E4B-it.gguf \
  --model-draft gemma-4-E4B-it-qat-assistant-q4_k_m.gguf \
  --spec-type draft-mtp \
  --spec-draft-n-max 3

Files

gemma-4-E4B-it-qat-assistant-bf16.gguf
gemma-4-E4B-it-qat-assistant-q8_0.gguf
gemma-4-E4B-it-qat-assistant-q4_k_m.gguf
gemma-4-E4B-it-qat-assistant-q4_0.gguf

Conversion

BF16 source GGUF:

python convert_hf_to_gguf.py \
  google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant \
  --outfile gemma-4-E4B-it-qat-assistant-bf16.gguf \
  --outtype bf16

Q4_K_M and Q4_0 were quantized directly from the BF16 GGUF:

llama-quantize gemma-4-E4B-it-qat-assistant-bf16.gguf gemma-4-E4B-it-qat-assistant-q4_k_m.gguf q4_k_m
llama-quantize gemma-4-E4B-it-qat-assistant-bf16.gguf gemma-4-E4B-it-qat-assistant-q4_0.gguf q4_0

Q8_0 was exported directly from the Hugging Face checkpoint:

python convert_hf_to_gguf.py \
  google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant \
  --outfile gemma-4-E4B-it-qat-assistant-q8_0.gguf \
  --outtype q8_0

Downloads last month: 834

GGUF

Model size

78M params

Architecture

gemma4-assistant

Hardware compatibility

4-bit

8-bit

16-bit

Inference Providers NEW

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

Model tree for cascade-tech/gemma-4-E4B-it-qat-q4_0-unquantized-assistant-gguf

Base model

google/gemma-4-E4B-it-assistant

Finetuned

google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant

Quantized

(11)

this model