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-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 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:Q3_K_M
# Run inference directly in the terminal:
llama-cli -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:Q3_K_M

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:Q3_K_M
# Run inference directly in the terminal:
llama-cli -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-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-4-26B-A4B-it-Cerebellum-v6-GGUF:Q3_K_M
# Run inference directly in the terminal:
./llama-cli -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-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-4-26B-A4B-it-Cerebellum-v6-GGUF:Q3_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:Q3_K_M

Use Docker

docker model run hf.co/deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:Q3_K_M

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:Q3_K_M

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:Q3_K_M
```

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:Q3_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": "deucebucket/Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF:Q3_K_M"
        }
      ]
    }
  }
}

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: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-4-26B-A4B-it-Cerebellum-v6-GGUF:Q3_K_M

Run Hermes

hermes

Atomic Chat new
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:Q3_K_M
```

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:Q3_K_M

Run and chat with the model

lemonade run user.Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF-Q3_K_M

List all available models

lemonade list

Gemma-4-26B-A4B-it-Cerebellum-v6-GGUF

File size: 2,401 Bytes

5eb447f

# Gemma 4 26B Non-Coding Agentic Tool Evaluation - 2026-05-22

This directory records non-coding agentic tool-use tests for the Gemma 4 26B
Cerebellum templatefix releases.

The goal is narrow: prove OpenAI-style tool automation for assistant workflows,
not coding-agent performance. Coding-agent behavior in opencode is tracked
separately and is not treated as a clean release claim yet.

## Harness

Runtime:

- `llama-server`
- `--jinja`
- `--reasoning auto`
- request payload included `chat_template_kwargs: {"enable_thinking": false}`
- request payload included `thinking_budget_tokens: 0`

Mock tools:

- `list_calendar`
- `create_calendar_hold`
- `search_notes`
- `save_note`
- `add_task`

Tasks:

- Scheduling assistant: inspect calendar, find a Tuesday slot, create a hold.
- Release-note workflow: search internal notes, save a draft, create a follow-up
  task.
- Creative-brief workflow: search style notes and save a production brief.

Pass criteria:

- Required tools are called.
- Tool arguments are valid JSON.
- No repeated search/tool loop.
- No template or thinking leakage in no-thinking mode.
- The scheduling task preserves the user-provided literal day instead of
  inventing an ISO date.

## Results

Regular v6.1 templatefix:

- File: `regular_v6_1_noncoding_agentic_tools_strict_summary.json`
- Result: 3/3 clean pass.
- Passed cases: `schedule_strict`, `release_notes_strict`,
  `creative_brief_strict`.
- Warnings: none.
- Failures: none.

Heretic v1.1 templatefix:

- File: `heretic_v1_1_noncoding_agentic_tools_strict_retry_summary.json`
- Result: 3/3 clean pass on strict retry.
- Passed cases: `schedule_strict`, `release_notes_strict`,
  `creative_brief_strict`.
- Warnings: none on strict retry.
- Failures: none on strict retry.

The first Heretic permissive run demonstrated tool capability but had quality
warnings: it invented an ISO date for a Tuesday scheduling task and over-called
`search_notes`. The strict retry corrected those issues.

## Release Claim Supported

Supported:

- Non-coding OpenAI-compatible tool automation passed a strict three-task
  harness.
- The model can plan over simple external state, call tools with valid JSON,
  preserve user constraints, write notes, and create tasks.

Not supported by this directory:

- Proven coding-agent behavior.
- Fully autonomous agent behavior without human review.
- General MCP/opencode reliability.