Instructions to use amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF 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 amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf amaranus/Gemma-4-E4B-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 serve -hf amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama cli -hf amaranus/Gemma-4-E4B-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 amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf amaranus/Gemma-4-E4B-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 amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

LM Studio
Jan
Ollama
How to use amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF with Ollama:
```
ollama run hf.co/amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
```
Unsloth Desktop

How to use amaranus/Gemma-4-E4B-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 serve -hf amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

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": "amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0
```

Lemonade

How to use amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF-Q8_0

List all available models

lemonade list

Hermes Agent

How to use amaranus/Gemma-4-E4B-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 serve -hf amaranus/Gemma-4-E4B-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 amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0

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 "amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF:Q8_0" \
  --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-E4B-it-qat-q4_0-unquantized-assistant - GGUF Quantized Model

This model is a GGUF quantized version of the google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant base model, converted using llama.cpp's https://github.com/ggml-org/llama.cpp/blob/master/convert_hf_to_gguf.py script.

Quantization Details

Base Model: google/gemma-4-E4B-it-qat-q4_0-unquantized-assistant
Conversion Tool: llama.cpp https://github.com/ggml-org/llama.cpp/blob/master/convert_hf_to_gguf.py
Quantization Method: Q8_0 (8-bit quantization)
Format: GGUF (GPT-Generated Unified Format)

Model Files

File	Description
`gemma-4-E4B-it-qat-assistant-MTP-Q8_0.gguf`	Draft model for speculative decoding (Q8_0)

Usage with llama-server

Below is the recommended llama-server command to run this model with optimal settings including MTP (Multi-Token Prediction) speculative decoding:

llama-server -hf google/gemma-4-E4B-it-qat-q4_0-gguf \
  --temp 1.0 \
  --top-p 0.95 \
  --top-k 64 \
  --ui-mcp-proxy \
  -c 64000 \
  -fa off \
  --jinja \
  --metrics \
  --spec-type draft-mtp \
  --spec-draft-n-max 2 \
  --parallel 1 \
  --spec-draft-hf amaranus/Gemma-4-E4B-it-qat-assistant-MTP-Q8_0-GGUF

Parameter	Value	Description
`-hf`	`google/gemma-4-E4B-it-qat-q4_0-gguf`	Load model directly from Hugging Face Hub
`--temp`	`1.0`	Sampling temperature (higher = more creative)
`--top-p`	`0.95`	Nucleus sampling threshold
`--top-k`	`64`	Top-K sampling (only consider top 64 tokens)
`--ui-mcp-proxy`	`-`	Enable UI MCP proxy interface
`-c`	`64000`	Context length (64K tokens)
`-fa`	`off`	Flash Attention disabled (use standard attention)
`--jinja`	`-`	Enable Jinja2 template processing for chat formats
`--metrics`	`-`	Enable metrics endpoint for monitoring
`--spec-type`	`draft-mtp`	Speculative decoding type: Multi-Token Prediction
`--spec-draft-n-max`	`2`	Maximum number of speculative tokens per step
`--parallel`	`1`	Parallel sequences (1 = single sequence)
`--model-draft`	`gemma-4-E4B-it-qat-assistant-MTP-Q8_0.gguf`	Path to draft model (higher quality Q8_0)