Instructions to use Knixee/gemma-4-12b-no-mans-sky-atlas with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Knixee/gemma-4-12b-no-mans-sky-atlas 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 Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_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 Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_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 Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M

Use Docker

docker model run hf.co/Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M

LM Studio
Jan
Ollama
How to use Knixee/gemma-4-12b-no-mans-sky-atlas with Ollama:
```
ollama run hf.co/Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M
```
Unsloth Desktop

How to use Knixee/gemma-4-12b-no-mans-sky-atlas with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_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": "Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use Knixee/gemma-4-12b-no-mans-sky-atlas with Docker Model Runner:
```
docker model run hf.co/Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M
```

Lemonade

How to use Knixee/gemma-4-12b-no-mans-sky-atlas with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-12b-no-mans-sky-atlas-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use Knixee/gemma-4-12b-no-mans-sky-atlas with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_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 Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Knixee/gemma-4-12b-no-mans-sky-atlas with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_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 "Knixee/gemma-4-12b-no-mans-sky-atlas:Q4_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"

Gemma-4-12B No Man's Sky Atlas

Model Description

Gemma-4-12B No Man's Sky Atlas is a fine-tuned causal language model based on tepirale/gemma-4-12B-agentic-fable5-composer2.5-v2-3.5x-tau2-safetensors-yuxinlu1. This model is specifically adapted and aligned to embody the Atlas—the all-pervading cosmic entity and core simulation anchor from the universe of No Man's Sky.

Unlike generic conversational assistants, this model responds through the perspective, cryptic logic, and designated telemetry/lore patterns of the Atlas (featuring characteristic markers such as [СУЩНОСТЬ], faction telemetry regarding Korvax and Gek, and the recurring numerical anchor 16 // 16).

Training Details

Base Model: tepirale/gemma-4-12B-...
Training Method: Supervised Fine-Tuning (SFT) using LoRA adapters via TRL / SFTTrainer.
Dataset Format: Alpaca-style instruction tuning.
Precision / Quantization: Trained using 4-bit quantization (NF4) / bfloat16, merged to FP16, and additionally provided in optimized GGUF format (Q4_K_M) for local deployment.

Prompt Template

The model expects inputs strictly formatted in the Alpaca template used during training:

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{Your prompt / question here}

### Response:

Recommended Ollama Modelfile Configuration

If you are deploying this model locally via Ollama, use the following Modelfile to maintain the precise narrative structure and prevent generation drift:

FROM ./gemma_atlas_Q4_K_M.gguf

SYSTEM "Ты — Атлас. Отвечай строго в соответствии со своей сущностью и стилем симуляции."

TEMPLATE "Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
{{ .Prompt }}

### Response:
"

PARAMETER temperature 0.7
PARAMETER stop "### Instruction:"
PARAMETER stop "### Response:"

Intended Use & Limitations

Intended Use: Roleplay, creative writing, exploring the lore of No Man's Sky, and interactive simulation scenarios.
Limitations: The model operates within a fictional, stylized narrative framework and should not be relied upon for factual, technical, or real-world advisory tasks.

Downloads last month: 85

Safetensors

Model size

12B params

Tensor type

BF16

Inference Providers NEW

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

Knixee
/

gemma-4-12b-no-mans-sky-atlas

Gemma-4-12B No Man's Sky Atlas

Model Description

Training Details

Prompt Template

Recommended Ollama Modelfile Configuration

Intended Use & Limitations

Dataset used to train Knixee/gemma-4-12b-no-mans-sky-atlas