Instructions to use deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF",
	filename="gemma-4-26B-A4B-it-cerebellum-v6.1-templatefix.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 deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16
# Run inference directly in the terminal:
llama-cli -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16

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-4-26B-A4B-it-Cerebellum-v6-GGUF:F16
# Run inference directly in the terminal:
./llama-cli -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16

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-4-26B-A4B-it-Cerebellum-v6-GGUF:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16

Use Docker

docker model run hf.co/deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16

LM Studio
Jan

vLLM

How to use deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-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-4-26B-A4B-it-Cerebellum-v6-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16

Ollama
How to use deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF with Ollama:
```
ollama run hf.co/deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16
```

Unsloth Studio

How to use deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-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 deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-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 deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF to start chatting

How to use deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16

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": "deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16

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-4-26B-A4B-it-Cerebellum-v6-GGUF:F16

Run Hermes

hermes

Docker Model Runner
How to use deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF with Docker Model Runner:
```
docker model run hf.co/deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16
```

Lemonade

How to use deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:F16

Run and chat with the model

lemonade run user.Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF-F16

List all available models

lemonade list

deucebucket commited on 16 days ago

Commit

309efb7

verified ·

1 Parent(s): 5eb447f

docs: update templatefix test notes

Browse files

Files changed (1) hide show

agentic_eval_20260522/regular_v6_1_noncoding_agentic_tools_strict.jsonl +3 -0

agentic_eval_20260522/regular_v6_1_noncoding_agentic_tools_strict.jsonl ADDED Viewed

	@@ -0,0 +1,3 @@

+{"id": "schedule_strict", "status": "pass", "issues": [], "called_tools": ["list_calendar", "create_calendar_hold", "add_task"], "tool_calls": [{"name": "list_calendar", "args": {"day": "Tuesday"}, "result": {"events": [{"id": "cal-1", "day": "Tuesday", "start": "09:00", "end": "10:00", "title": "dentist"}, {"id": "cal-2", "day": "Tuesday", "start": "14:00", "end": "15:30", "title": "vendor call"}]}}, {"name": "create_calendar_hold", "args": {"day": "Tuesday", "end": "11:00", "start": "10:15", "title": "Free Slot Hold"}, "result": {"created": {"id": "cal-4", "day": "Tuesday", "end": "11:00", "start": "10:15", "title": "Free Slot Hold"}}}, {"name": "add_task", "args": {"evidence": "Created hold for Tuesday 10:15-11:00", "priority": "medium", "title": "Follow up on Tuesday hold"}, "result": {"added": {"id": "task-1", "evidence": "Created hold for Tuesday 10:15-11:00", "priority": "medium", "title": "Follow up on Tuesday hold"}}}], "final": "The Tuesday calendar was listed, showing a free slot between the \"dentist\" and \"vendor call\" appointments. I have created a 45-minute hold for Tuesday from 10:15 to 11:00 and added a follow-up task."}
+{"id": "release_notes_strict", "status": "pass", "issues": [], "called_tools": ["search_notes", "save_note", "add_task"], "tool_calls": [{"name": "search_notes", "args": {"query": "release checklist Carl preferences"}, "result": {"hits": []}}, {"name": "save_note", "args": {"body": "Internal release-note draft: Review checklist and Carl's preferences for the upcoming release.", "title": "Internal Release-Note Draft"}, "result": {"saved": "Internal Release-Note Draft"}}, {"name": "add_task", "args": {"evidence": "Missing proof for release checklist.", "priority": "high", "title": "Obtain missing proof for release checklist"}, "result": {"added": {"id": "task-2", "evidence": "Missing proof for release checklist.", "priority": "high", "title": "Obtain missing proof for release checklist"}}}], "final": "I have searched for the notes, saved a concise internal release-note draft, and added a high-priority task for the missing proof."}
+{"id": "creative_brief_strict", "status": "pass", "issues": [], "called_tools": ["search_notes", "save_note"], "tool_calls": [{"name": "search_notes", "args": {"query": "style guide"}, "result": {"hits": []}}, {"name": "save_note", "args": {"body": "Production Creative Brief: Romantic Stormlit Apartment Scene\nTone: Intimate, atmospheric, and non-explicit.\nVisual Style: Low-key lighting, heavy use of shadows, and blue/cool tones from the storm outside contrasted with warm, amber hues from indoor lamps.\nSetting: A cozy apartment during a thunderstorm. Large windows showing rain and lightning.\nKey Elements: Sound of rain against glass, soft textures (blankets, velvet), flickering candlelight, and subtle character interaction.\nGoal: Capture the tension and romance through atmosphere and subtext rather than explicit action.", "title": "Production Creative Brief - Romantic Stormlit Apartment Scene"}, "result": {"saved": "Production Creative Brief - Romantic Stormlit Apartment Scene"}}], "final": "The production creative brief for the non-explicit romantic stormlit apartment scene has been saved."}