Instructions to use saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-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 saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-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 saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-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 saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-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 saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-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 saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF:Q4_K_M

Use Docker

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

LM Studio
Jan
Ollama
How to use saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF:Q4_K_M
```
Unsloth Desktop

How to use saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

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

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": "saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

How to use saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF with Lemonade:

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

Hermes Agent

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

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF with OpenClaw:

Start the llama.cpp server

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

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 "saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF:Q4_K_M" \
  --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 21B-A4B-IT REAP — Q4_K_M GGUF

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

What is REAP?

Router-weighted Expert Activation Pruning — removes the 20% least important MoE experts (25 of 128 → 103 remaining) using calibration-based scoring. Unlike quantization, REAP removes entire experts while keeping the same active parameter count (~4B) per token.

Model Details

Property	Value
Base Model	google/gemma-4-26b-a4b-it
Pruning	REAP 0.20 (103/128 experts)
Quantization	Q4_K_M (5.32 BPW)
File Size	12.87 GB
Total Parameters	20.77B
Active Parameters	~4B per token
Context Window	262,144 tokens
Architecture	Gemma4 MoE (30 layers)

Performance

Tested on RTX 4070 Ti SUPER (16GB VRAM):

Speed: 65-95 tokens/second
VRAM Usage: ~14.8 GB (fits 16GB cards)
Full GPU offload with (KV cache in system RAM)

How to Run (llama.cpp)

Conversion

Converted from BF16 safetensors → F16 GGUF using llama.cpp convert_hf_to_gguf.py, then quantized with llama-quantize to Q4_K_M.

Downloads last month: 74

GGUF

Model size

21B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for saria-lh/gemma-4-21b-a4b-it-REAP-Q4_K_M-GGUF

Base model

0xSero/Gemma-4-21B

Quantized

(11)

this model