Instructions to use vsark/gemma-4-21b-a4b-it-REAP-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 vsark/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 vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S
# Run inference directly in the terminal:
llama cli -hf vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S
# Run inference directly in the terminal:
llama cli -hf vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S

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 vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S
# Run inference directly in the terminal:
./llama-cli -hf vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S

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 vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S
# Run inference directly in the terminal:
./build/bin/llama-cli -hf vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S

Use Docker

docker model run hf.co/vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S

LM Studio
Jan
Ollama
How to use vsark/gemma-4-21b-a4b-it-REAP-GGUF with Ollama:
```
ollama run hf.co/vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S
```

Unsloth Studio

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

How to use vsark/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 vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S

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": "vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S

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 "vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S" \
  --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"

Docker Model Runner
How to use vsark/gemma-4-21b-a4b-it-REAP-GGUF with Docker Model Runner:
```
docker model run hf.co/vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S

Run and chat with the model

lemonade run user.gemma-4-21b-a4b-it-REAP-GGUF-Q3_K_S

List all available models

lemonade list

Hermes Agent

How to use vsark/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 vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S

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 vsark/gemma-4-21b-a4b-it-REAP-GGUF:Q3_K_S

Run Hermes

hermes

Atomic Chat

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

GGUF quantizations of 0xSero/gemma-4-21b-a4b-it-REAP — a 20% expert-pruned Gemma 4 using Cerebras REAP.

If you have 16GB VRAM or less, consider the 19B variant instead — it's dramatically faster due to VRAM headroom.

Available Quantizations

File	Quant	Size	BPW	Use Case
`gemma-4-21b-reap-Q4_K_M.gguf`	Q4_K_M	13 GB	5.32	Recommended. Best quality/size tradeoff.
`gemma-4-21b-reap-Q3_K_S.gguf`	Q3_K_S	9.5 GB	3.89	Fits tighter VRAM budgets.

Performance (AMD RX 9070 XT, 16GB VRAM, Vulkan)

Metric	Original 26B Q4_K_M	REAP 21B Q4_K_M
Speed	17 tok/s	18 tok/s (+5-8%)
Disk	16 GB	13 GB (-19%)
Max context @ 16GB	~4k	~8k
Quality	Baseline	Indistinguishable

Note: On 16GB cards the 21B Q4_K_M still hits 99% VRAM, limiting the speedup. The 19B variant drops to 76% VRAM and runs 7x faster. The 21B shines on 24GB+ cards where VRAM isn't the bottleneck.

Quick Start

# Download
hf download vsark/gemma-4-21b-a4b-it-REAP-GGUF gemma-4-21b-reap-Q4_K_M.gguf

# Run (IMPORTANT: use --reasoning off for Gemma 4)
llama-server \
    --model gemma-4-21b-reap-Q4_K_M.gguf \
    --n-gpu-layers 99 \
    --ctx-size 8192 \
    --reasoning off \
    --host 127.0.0.1 --port 8012

Important Notes

Use --reasoning off with llama-server
Requires recent llama.cpp with gemma4 architecture support
20% pruning preserves more knowledge than the 30% variant — better for trivia/knowledge-intensive tasks

Verification

SHA256 checksums:

926f03ac6a1995d72e05b1dc08025dae47a447469b5ccf9840bcce2846c54e55  gemma-4-21b-reap-Q4_K_M.gguf
30ee2997d7ecd3fd8ef5ad04ce9a1890f3ab2536ae8da9ab50985a810456fd63  gemma-4-21b-reap-Q3_K_S.gguf

Credits

REAP pruning: 0xSero
Base model: Google Gemma 4
GGUF conversion + benchmarks: vsark

Downloads last month: 77

GGUF

Model size

21B params

Architecture

gemma4

Hardware compatibility

3-bit

4-bit

Inference Providers NEW

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

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

Base model

0xSero/Gemma-4-21B

Quantized

(11)

this model