Instructions to use deucebucket/Gemma-4-E4B-it-Cerebellum-v2-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 deucebucket/Gemma-4-E4B-it-Cerebellum-v2-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 deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M
# Run inference directly in the terminal:
llama cli -hf deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_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 deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_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 deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M

Use Docker

docker model run hf.co/deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M

LM Studio
Jan

vLLM

How to use deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deucebucket/Gemma-4-E4B-it-Cerebellum-v2-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": "deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M

Ollama
How to use deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF with Ollama:
```
ollama run hf.co/deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M
```
Unsloth Desktop

How to use deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_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": "deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF with Docker Model Runner:
```
docker model run hf.co/deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M
```

Lemonade

How to use deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M

Run and chat with the model

lemonade run user.Gemma-4-E4B-it-Cerebellum-v2-GGUF-Q3_K_M

List all available models

lemonade list

Hermes Agent

How to use deucebucket/Gemma-4-E4B-it-Cerebellum-v2-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 deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_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 deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_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 "deucebucket/Gemma-4-E4B-it-Cerebellum-v2-GGUF:Q3_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"

deucebucket commited on Apr 30

Commit

4baf411

verified ·

1 Parent(s): 8878f78

Cerebellum v2 tensor overrides (174 PLE Q5_K + 2 Q6_K + 3 Q2_K)

Browse files

Files changed (1) hide show

cerebellum_v2_overrides.txt +179 -0

cerebellum_v2_overrides.txt ADDED Viewed

	@@ -0,0 +1,179 @@

+per_layer_token_embd.weight=Q5_K
+blk.0.inp_gate.weight=Q5_K
+blk.0.proj.weight=Q5_K
+blk.1.inp_gate.weight=Q5_K
+blk.1.proj.weight=Q5_K
+blk.10.inp_gate.weight=Q5_K
+blk.10.proj.weight=Q5_K
+blk.11.inp_gate.weight=Q5_K
+blk.11.proj.weight=Q5_K
+blk.12.inp_gate.weight=Q5_K
+blk.12.proj.weight=Q5_K
+blk.13.inp_gate.weight=Q5_K
+blk.13.proj.weight=Q5_K
+blk.14.inp_gate.weight=Q5_K
+blk.14.proj.weight=Q5_K
+blk.15.inp_gate.weight=Q5_K
+blk.15.proj.weight=Q5_K
+blk.16.inp_gate.weight=Q5_K
+blk.16.proj.weight=Q5_K
+blk.17.inp_gate.weight=Q5_K
+blk.17.proj.weight=Q5_K
+blk.18.inp_gate.weight=Q5_K
+blk.18.proj.weight=Q5_K
+blk.19.inp_gate.weight=Q5_K
+blk.19.proj.weight=Q5_K
+blk.2.inp_gate.weight=Q5_K
+blk.2.proj.weight=Q5_K
+blk.20.inp_gate.weight=Q5_K
+blk.20.proj.weight=Q5_K
+blk.21.inp_gate.weight=Q5_K
+blk.21.proj.weight=Q5_K
+blk.22.inp_gate.weight=Q5_K
+blk.22.proj.weight=Q5_K
+blk.23.inp_gate.weight=Q5_K
+blk.23.proj.weight=Q5_K
+blk.24.inp_gate.weight=Q5_K
+blk.24.proj.weight=Q5_K
+blk.25.inp_gate.weight=Q5_K
+blk.25.proj.weight=Q5_K
+blk.26.inp_gate.weight=Q5_K
+blk.26.proj.weight=Q5_K
+blk.27.inp_gate.weight=Q5_K
+blk.27.proj.weight=Q5_K
+blk.28.inp_gate.weight=Q5_K
+blk.28.proj.weight=Q5_K
+blk.29.inp_gate.weight=Q5_K
+blk.29.proj.weight=Q5_K
+blk.3.inp_gate.weight=Q5_K
+blk.3.proj.weight=Q5_K
+blk.30.inp_gate.weight=Q5_K
+blk.30.proj.weight=Q5_K
+blk.31.inp_gate.weight=Q5_K
+blk.31.proj.weight=Q5_K
+blk.32.inp_gate.weight=Q5_K
+blk.32.proj.weight=Q5_K
+blk.33.inp_gate.weight=Q5_K
+blk.33.proj.weight=Q5_K
+blk.34.inp_gate.weight=Q5_K
+blk.34.proj.weight=Q5_K
+blk.35.inp_gate.weight=Q5_K
+blk.35.proj.weight=Q5_K
+blk.36.inp_gate.weight=Q5_K
+blk.36.proj.weight=Q5_K
+blk.37.inp_gate.weight=Q5_K
+blk.37.proj.weight=Q5_K
+blk.38.inp_gate.weight=Q5_K
+blk.38.proj.weight=Q5_K
+blk.39.inp_gate.weight=Q5_K
+blk.39.proj.weight=Q5_K
+blk.4.inp_gate.weight=Q5_K
+blk.4.proj.weight=Q5_K
+blk.40.inp_gate.weight=Q5_K
+blk.40.proj.weight=Q5_K
+blk.41.inp_gate.weight=Q5_K
+blk.41.proj.weight=Q5_K
+blk.5.inp_gate.weight=Q5_K
+blk.5.proj.weight=Q5_K
+blk.6.inp_gate.weight=Q5_K
+blk.6.proj.weight=Q5_K
+blk.7.inp_gate.weight=Q5_K
+blk.7.proj.weight=Q5_K
+blk.8.inp_gate.weight=Q5_K
+blk.8.proj.weight=Q5_K
+blk.9.inp_gate.weight=Q5_K
+blk.9.proj.weight=Q5_K
+per_layer_model_proj.weight=Q5_K
+per_layer_proj_norm.weight=Q5_K
+per_layer_token_embd.weight=Q5_K
+blk.0.inp_gate.weight=Q5_K
+blk.0.proj.weight=Q5_K
+blk.1.inp_gate.weight=Q5_K
+blk.1.proj.weight=Q5_K
+blk.10.inp_gate.weight=Q5_K
+blk.10.proj.weight=Q5_K
+blk.11.inp_gate.weight=Q5_K
+blk.11.proj.weight=Q5_K
+blk.12.inp_gate.weight=Q5_K
+blk.12.proj.weight=Q5_K
+blk.13.inp_gate.weight=Q5_K
+blk.13.proj.weight=Q5_K
+blk.14.inp_gate.weight=Q5_K
+blk.14.proj.weight=Q5_K
+blk.15.inp_gate.weight=Q5_K
+blk.15.proj.weight=Q5_K
+blk.16.inp_gate.weight=Q5_K
+blk.16.proj.weight=Q5_K
+blk.17.inp_gate.weight=Q5_K
+blk.17.proj.weight=Q5_K
+blk.18.inp_gate.weight=Q5_K
+blk.18.proj.weight=Q5_K
+blk.19.inp_gate.weight=Q5_K
+blk.19.proj.weight=Q5_K
+blk.2.inp_gate.weight=Q5_K
+blk.2.proj.weight=Q5_K
+blk.20.inp_gate.weight=Q5_K
+blk.20.proj.weight=Q5_K
+blk.21.inp_gate.weight=Q5_K
+blk.21.proj.weight=Q5_K
+blk.22.inp_gate.weight=Q5_K
+blk.22.proj.weight=Q5_K
+blk.23.inp_gate.weight=Q5_K
+blk.23.proj.weight=Q5_K
+blk.24.inp_gate.weight=Q5_K
+blk.24.proj.weight=Q5_K
+blk.25.inp_gate.weight=Q5_K
+blk.25.proj.weight=Q5_K
+blk.26.inp_gate.weight=Q5_K
+blk.26.proj.weight=Q5_K
+blk.27.inp_gate.weight=Q5_K
+blk.27.proj.weight=Q5_K
+blk.28.inp_gate.weight=Q5_K
+blk.28.proj.weight=Q5_K
+blk.29.inp_gate.weight=Q5_K
+blk.29.proj.weight=Q5_K
+blk.3.inp_gate.weight=Q5_K
+blk.3.proj.weight=Q5_K
+blk.30.inp_gate.weight=Q5_K
+blk.30.proj.weight=Q5_K
+blk.31.inp_gate.weight=Q5_K
+blk.31.proj.weight=Q5_K
+blk.32.inp_gate.weight=Q5_K
+blk.32.proj.weight=Q5_K
+blk.33.inp_gate.weight=Q5_K
+blk.33.proj.weight=Q5_K
+blk.34.inp_gate.weight=Q5_K
+blk.34.proj.weight=Q5_K
+blk.35.inp_gate.weight=Q5_K
+blk.35.proj.weight=Q5_K
+blk.36.inp_gate.weight=Q5_K
+blk.36.proj.weight=Q5_K
+blk.37.inp_gate.weight=Q5_K
+blk.37.proj.weight=Q5_K
+blk.38.inp_gate.weight=Q5_K
+blk.38.proj.weight=Q5_K
+blk.39.inp_gate.weight=Q5_K
+blk.39.proj.weight=Q5_K
+blk.4.inp_gate.weight=Q5_K
+blk.4.proj.weight=Q5_K
+blk.40.inp_gate.weight=Q5_K
+blk.40.proj.weight=Q5_K
+blk.41.inp_gate.weight=Q5_K
+blk.41.proj.weight=Q5_K
+blk.5.inp_gate.weight=Q5_K
+blk.5.proj.weight=Q5_K
+blk.6.inp_gate.weight=Q5_K
+blk.6.proj.weight=Q5_K
+blk.7.inp_gate.weight=Q5_K
+blk.7.proj.weight=Q5_K
+blk.8.inp_gate.weight=Q5_K
+blk.8.proj.weight=Q5_K
+blk.9.inp_gate.weight=Q5_K
+blk.9.proj.weight=Q5_K
+per_layer_model_proj.weight=Q5_K
+per_layer_proj_norm.weight=Q5_K
+blk.41.attn_q.weight=Q6_K
+blk.20.ffn_up.weight=Q6_K
+blk.15.ffn_gate.weight=Q2_K
+blk.40.attn_q.weight=Q2_K
+blk.41.ffn_up.weight=Q2_K