Instructions to use GermannM/Kenga-Coder-7B-Z with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use GermannM/Kenga-Coder-7B-Z with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use GermannM/Kenga-Coder-7B-Z 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 GermannM/Kenga-Coder-7B-Z:IQ3_M
# Run inference directly in the terminal:
llama cli -hf GermannM/Kenga-Coder-7B-Z:IQ3_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf GermannM/Kenga-Coder-7B-Z:IQ3_M
# Run inference directly in the terminal:
llama cli -hf GermannM/Kenga-Coder-7B-Z:IQ3_M

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 GermannM/Kenga-Coder-7B-Z:IQ3_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf GermannM/Kenga-Coder-7B-Z:IQ3_M

Use Docker

docker model run hf.co/GermannM/Kenga-Coder-7B-Z:IQ3_M

Llama new
LM Studio
Jan

vLLM

How to use GermannM/Kenga-Coder-7B-Z with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "GermannM/Kenga-Coder-7B-Z"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "GermannM/Kenga-Coder-7B-Z",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/GermannM/Kenga-Coder-7B-Z:IQ3_M

Ollama
How to use GermannM/Kenga-Coder-7B-Z with Ollama:
```
ollama run hf.co/GermannM/Kenga-Coder-7B-Z:IQ3_M
```
Unsloth Desktop

How to use GermannM/Kenga-Coder-7B-Z with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GermannM/Kenga-Coder-7B-Z:IQ3_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": "GermannM/Kenga-Coder-7B-Z:IQ3_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use GermannM/Kenga-Coder-7B-Z with Docker Model Runner:
```
docker model run hf.co/GermannM/Kenga-Coder-7B-Z:IQ3_M
```

Lemonade

How to use GermannM/Kenga-Coder-7B-Z with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull GermannM/Kenga-Coder-7B-Z:IQ3_M

Run and chat with the model

lemonade run user.Kenga-Coder-7B-Z-IQ3_M

List all available models

lemonade list

Hermes Agent

How to use GermannM/Kenga-Coder-7B-Z with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GermannM/Kenga-Coder-7B-Z:IQ3_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 GermannM/Kenga-Coder-7B-Z:IQ3_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use GermannM/Kenga-Coder-7B-Z with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf GermannM/Kenga-Coder-7B-Z:IQ3_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 "GermannM/Kenga-Coder-7B-Z:IQ3_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"

Kenga-Coder-7B-Z

File size: 2,102 Bytes

a6cc17e

---
license: apache-2.0
base_model: Qwen/Qwen2.5-Coder-7B-Instruct
library_name: peft
language:
- ru
- en
- multilingual
tags:
- kenga
- kenga-lang
- z-system
- z-bl
- prophet
- eco-z
- russian
- code
- gguf
- ollama
pipeline_tag: text-generation
---

# Kenga-Coder-7B-Z — 7.6B кодер Кенги (Z-BL + Prophet M5.3/rp1 + Eco-Z 3.3GB)

**Kenga-Coder-7B-Z** — 7.6-миллиардная модель Кенги для видеокарт **4–6 ГБ VRAM (GTX 1660 и ноутбуков)**, обученная по полному протоколу старшей модели `Kenga-Coder-14B-Z`:
- **Самоидентификация (вшита в веса и `chat_template`):** Кенга (Кенга-Кодер), создал Герман (`GermannM`) в Москве, любит Россию, отвечает прямо и коротко.
- **Z-BL адаптер (`ΔW = U · diag(S · mask) · Vᵀ`):** QR-инициализация, расписание ранга `8 → 16 → 32`, спектральная энтропия адаптера **`mean_H = 2.9412`** из `3.4657` (~85% равномерного использования спектра).
- **Assistant-only Loss + `NO_SYS_P = 0.30`:** корпус `train4.jsonl` (8917 диалогов: `m53_binding`, `rp1_repair <FIX>`, `kenga-grammar`, 25 языков программирования).
- **Спектральный маркер (`z_marker`):** `ddce2488042ab7bb`.

## Файлы (квантованы с `imatrix`)

- `kenga-coder-7b-z-q4_k_m.gguf` (**4.36 ГБ**) — основной квант для **6 ГБ видеокарт (GTX 1660)**.
- `kenga-coder-7b-z-eco-iq3_m.gguf` (**3.33 ГБ**) — сверхлёгкий квант **Eco-Z** для **4 ГБ видеокарт и CPU**.
- `kenga_passport.json` — спектральный паспорт модели.
- `adapter/` — Z-BL адаптер в формате PEFT.

## Запуск

```bash
ollama run hf.co/GermannM/Kenga-Coder-7B-Z:Q4_K_M
```

---
Создатель: **Герман Янтарас (GermannM)** · Москва, Россия