Instructions to use optima-tools-ch/chat-low with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use optima-tools-ch/chat-low 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 optima-tools-ch/chat-low:Q4_0
# Run inference directly in the terminal:
llama cli -hf optima-tools-ch/chat-low:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf optima-tools-ch/chat-low:Q4_0
# Run inference directly in the terminal:
llama cli -hf optima-tools-ch/chat-low:Q4_0

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf optima-tools-ch/chat-low:Q4_0
# Run inference directly in the terminal:
./build/bin/llama cli -hf optima-tools-ch/chat-low:Q4_0

Use Docker

docker model run hf.co/optima-tools-ch/chat-low:Q4_0

Llama new
LM Studio
Jan

vLLM

How to use optima-tools-ch/chat-low with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "optima-tools-ch/chat-low"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "optima-tools-ch/chat-low",
		"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/optima-tools-ch/chat-low:Q4_0

Ollama
How to use optima-tools-ch/chat-low with Ollama:
```
ollama run hf.co/optima-tools-ch/chat-low:Q4_0
```
Unsloth Desktop

How to use optima-tools-ch/chat-low with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf optima-tools-ch/chat-low:Q4_0

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": "optima-tools-ch/chat-low:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use optima-tools-ch/chat-low with Docker Model Runner:
```
docker model run hf.co/optima-tools-ch/chat-low:Q4_0
```

Lemonade

How to use optima-tools-ch/chat-low with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull optima-tools-ch/chat-low:Q4_0

Run and chat with the model

lemonade run user.chat-low-Q4_0

List all available models

lemonade list

Hermes Agent

How to use optima-tools-ch/chat-low with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf optima-tools-ch/chat-low:Q4_0

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 optima-tools-ch/chat-low:Q4_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use optima-tools-ch/chat-low with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf optima-tools-ch/chat-low:Q4_0

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 "optima-tools-ch/chat-low:Q4_0" \
  --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"

chat-low

File size: 2,975 Bytes

c83eb5d

{
  "schemaVersion": 1,
  "preparedAt": "2026-10-27T20:37:56.954Z",
  "preparedBy": "Optima Tools (optima-tools-ch)",
  "package": {
    "id": "chat.low",
    "repository": "optima-tools-ch/chat-low",
    "usage": "Chat et raisonnement",
    "level": "low",
    "name": "Gemma 4 E4B QAT Q4_0 + vision"
  },
  "source": {
    "host": "huggingface.co",
    "repository": "google/gemma-4-E4B-it-qat-q4_0-gguf",
    "revision": "4b4a2c1d584be7264f87aac328a1bc739ce81b6c",
    "url": "https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-gguf/tree/4b4a2c1d584be7264f87aac328a1bc739ce81b6c",
    "baseModel": "google/gemma-4-E4B-it-qat-q4_0-unquantized",
    "authors": [
      "Google DeepMind"
    ],
    "license": "Apache-2.0",
    "licenseUrl": "https://www.apache.org/licenses/LICENSE-2.0.txt",
    "licenseLinkInModelCard": "https://ai.google.dev/gemma/docs/gemma_4_license"
  },
  "transfer": {
    "method": "Duplication des fichiers LFS côté serveur Hugging Face (copie par empreinte), puis commit dans le dépôt de destination",
    "downloadedLocally": false,
    "modifiedFiles": false
  },
  "files": [
    {
      "path": "gemma-4-E4B_q4_0-it.gguf",
      "role": "model",
      "sizeBytes": 5154941280,
      "sha256": "676c35070db6dbe52f93e9c864ee0fba4eddea94b9c875d9cb10daff453fbaee",
      "sourceUrl": "https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-gguf/resolve/4b4a2c1d584be7264f87aac328a1bc739ce81b6c/gemma-4-E4B_q4_0-it.gguf",
      "sourcePath": "gemma-4-E4B_q4_0-it.gguf",
      "verification": {
        "sha256": "Empreinte SHA-256 lue dans les métadonnées LFS de Hugging Face, identique sur la source et la destination",
        "recomputedLocally": false
      }
    },
    {
      "path": "gemma-4-E4B-it-mmproj.gguf",
      "role": "multimodal-projector",
      "sizeBytes": 991552256,
      "sha256": "7498a37cb619e55f2fcf87eb931f56e99389ed6d432e4c5c66110694c0d65578",
      "sourceUrl": "https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-gguf/resolve/4b4a2c1d584be7264f87aac328a1bc739ce81b6c/gemma-4-E4B-it-mmproj.gguf",
      "sourcePath": "gemma-4-E4B-it-mmproj.gguf",
      "verification": {
        "sha256": "Empreinte SHA-256 lue dans les métadonnées LFS de Hugging Face, identique sur la source et la destination",
        "recomputedLocally": false
      }
    }
  ],
  "documents": [
    {
      "path": "README-Google.md",
      "sizeBytes": 29233,
      "sha256": "6c8dbc23d482d76d6a02e6804941fae6dccdcd20e6372c26e4dec35e21348607",
      "origin": "https://huggingface.co/google/gemma-4-E4B-it-qat-q4_0-gguf/resolve/4b4a2c1d584be7264f87aac328a1bc739ce81b6c/README.md",
      "note": "README officiel de la révision, copie identique"
    },
    {
      "path": "LICENSE",
      "sizeBytes": 11358,
      "sha256": "cfc7749b96f63bd31c3c42b5c471bf756814053e847c10f3eb003417bc523d30",
      "origin": "https://www.apache.org/licenses/LICENSE-2.0.txt",
      "note": "Texte officiel de la licence Apache 2.0"
    }
  ]
}