Instructions to use Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF",
	filename="gemma-4-21b-a4b-it-REAP-Q3_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use Ayodele01/gemma-4-21b-a4b-it-REAP-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 Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Ayodele01/gemma-4-21b-a4b-it-REAP-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 Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Ayodele01/gemma-4-21b-a4b-it-REAP-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 Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M

Use Docker

docker model run hf.co/Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M

Ollama
How to use Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF with Ollama:
```
ollama run hf.co/Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M
```

Unsloth Studio

How to use Ayodele01/gemma-4-21b-a4b-it-REAP-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 Ayodele01/gemma-4-21b-a4b-it-REAP-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 Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF to start chatting

How to use Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Ayodele01/gemma-4-21b-a4b-it-REAP-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": "Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Ayodele01/gemma-4-21b-a4b-it-REAP-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 Ayodele01/gemma-4-21b-a4b-it-REAP-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 Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF with Docker Model Runner:
```
docker model run hf.co/Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M
```

Lemonade

How to use Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-21b-a4b-it-REAP-GGUF-Q4_K_M

List all available models

lemonade list

Gemma-4 21B-A4B-it REAP - GGUF

GGUF quantized versions of 0xSero/gemma-4-21b-a4b-it-REAP.

Model Description

This is 20% expert-pruned version of Google's Gemma-4 26B-A4B-it using Cerebras REAP (Router-weighted Expert Activation Pruning).

Key Specifications

Metric	Original (26B)	This Model (21B)
Total params	~26B	21.34B
Experts/layer	128	103
Active params/token	~4B	~4B
Disk size	~52GB	~43GB

REAP removes 20% of MoE experts (25 of 128 per layer) while preserving the model's routing behavior. The active parameter count per token is unchanged since the router still selects 8 experts per token from the remaining pool.

Architecture

30 transformer layers
Sliding attention (window=1024) for 25 layers, full attention every 6th layer
MoE FFN with 103 experts per layer, 8 active per token
Thinking model -- uses <|channel>thought / <|channel>response channels
Multimodal -- supports text and vision inputs
Context window: 262,144 tokens

Available Quantizations

Filename	Quant Type	Size	Description
`gemma-4-21b-a4b-it-REAP.gguf`	BF16	~43GB	Full precision, best quality
`gemma-4-21b-a4b-it-REAP-Q8_0.gguf`	Q8_0	~23GB	High quality
`gemma-4-21b-a4b-it-REAP-Q5_K_M.gguf`	Q5_K_M	~15GB	Balanced (recommended)
`gemma-4-21b-a4b-it-REAP-Q4_K_M.gguf`	Q4_K_M	~13GB	Good quality, smaller
`gemma-4-21b-a4b-it-REAP-Q3_K_M.gguf`	Q3_K_M	~10GB	Smallest

Usage with llama.cpp

# Download a quantized model
wget https://huggingface.co/Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF/resolve/main/gemma-4-21b-a4b-it-REAP-Q5_K_M.gguf

# Run with llama.cpp
./llama-cli -m gemma-4-21b-a4b-it-REAP-Q5_K_M.gguf \
  -p "Write a quicksort in Python." \
  -n 2048

Usage with Ollama

Create a Modelfile:

FROM ./gemma-4-21b-a4b-it-REAP-Q5_K_M.gguf

TEMPLATE """<bos><start_of_turn>user
{{ .Prompt }}<end_of_turn>
<start_of_turn>model
"""

PARAMETER stop "<end_of_turn>"
PARAMETER temperature 0.7

Then:

ollama create gemma4-21b-reap -f Modelfile
ollama run gemma4-21b-reap

Benchmark Results (from original REAP model)

Task	Original (26B)	REAP 21B
Elementary Math	92%	90%
Philosophy	92%	88%
GSM8K	86%	84%

Generation quality is "essentially indistinguishable from the original" according to the REAP authors.

License

This model is released under the Gemma License.

Credits

Original model: google/gemma-4-26b-a4b-it
REAP pruning: 0xSero/gemma-4-21b-a4b-it-REAP
REAP paper: arxiv.org/abs/2510.13999
GGUF conversion: Ayodele01

Downloads last month: 186

GGUF

Model size

21B params

Architecture

gemma4

Hardware compatibility

3-bit

4-bit

5-bit

8-bit

View +1 variant

Model tree for Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF

Base model

0xSero/Gemma-4-21B

Quantized

(11)

this model

Paper for Ayodele01/gemma-4-21b-a4b-it-REAP-GGUF

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Paper • 2510.13999 • Published Oct 15, 2025 • 20