Instructions to use KucLab/kuclab-hertz-0.9 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use KucLab/kuclab-hertz-0.9 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 KucLab/kuclab-hertz-0.9:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KucLab/kuclab-hertz-0.9:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf KucLab/kuclab-hertz-0.9:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf KucLab/kuclab-hertz-0.9: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 KucLab/kuclab-hertz-0.9:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf KucLab/kuclab-hertz-0.9: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 KucLab/kuclab-hertz-0.9:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf KucLab/kuclab-hertz-0.9:Q4_K_M

Use Docker

docker model run hf.co/KucLab/kuclab-hertz-0.9:Q4_K_M

LM Studio
Jan

vLLM

How to use KucLab/kuclab-hertz-0.9 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KucLab/kuclab-hertz-0.9"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KucLab/kuclab-hertz-0.9",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KucLab/kuclab-hertz-0.9:Q4_K_M

Ollama
How to use KucLab/kuclab-hertz-0.9 with Ollama:
```
ollama run hf.co/KucLab/kuclab-hertz-0.9:Q4_K_M
```
Unsloth Desktop

How to use KucLab/kuclab-hertz-0.9 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KucLab/kuclab-hertz-0.9: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": "KucLab/kuclab-hertz-0.9:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use KucLab/kuclab-hertz-0.9 with Docker Model Runner:
```
docker model run hf.co/KucLab/kuclab-hertz-0.9:Q4_K_M
```

Lemonade

How to use KucLab/kuclab-hertz-0.9 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull KucLab/kuclab-hertz-0.9:Q4_K_M

Run and chat with the model

lemonade run user.kuclab-hertz-0.9-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use KucLab/kuclab-hertz-0.9 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KucLab/kuclab-hertz-0.9: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 KucLab/kuclab-hertz-0.9:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use KucLab/kuclab-hertz-0.9 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf KucLab/kuclab-hertz-0.9: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 "KucLab/kuclab-hertz-0.9: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"

KucLab Hertz 0.9

A Czech/English STEM + programming assistant built by KucLab on top of Qwen/Qwen3.5-9B. Tuned 0.8: same API-teacher data, surgically cleaned (absurd premises and identity leaks removed, depth kept).

What this is

Base: Qwen/Qwen3.5-9B (~9B params, Apache 2.0)
Method: QLoRA, r=16 / alpha=32, merged to bf16 then quantized
Training data: 4700 rows — tuned 0.8 corpus (182 absurd/poison rows removed, 0 duplicates), 309 terminology rows, 28 answer-first examples, identity rows (Hertz 0.9)
Context: 32768 tokens (num_ctx)
Format: GGUF q4_k_m (~5.3GB)

Quickstart (Ollama)

curl -O https://huggingface.co/KucLab/kuclab-hertz-0.9/resolve/main/Modelfile
ollama create kuclab-hertz-0.9 -f Modelfile
ollama run kuclab-hertz-0.9

Benchmarks

Same harness throughout (240 MMLU-Pro STEM + 206 CZ terminology questions).

MMLU-Pro STEM

	Hertz 0.7F	Hertz 0.8	Hertz 0.9
Biology	83.3%	86.7%	85.0%
Chemistry	78.3%	83.3%	83.3%
Math	96.7%	95.0%	93.3%
Physics	75.0%	90.0%	85.0%
Total	83.3%	88.8%	86.7%

Czech terminology

	Hertz 0.7F	Hertz 0.8	Hertz 0.9
CS→EN	88.3%	87.4%	86.4%
EN→CS	82.5%	81.6%	87.4%
Total	85.4%	84.5%	86.9%

Honest status

✅ Best Czech of the line (86.9%, EN→CS 87.4%)
⚠️ STEM 86.7% below 0.8's 88.8% — cleaning cost some physics depth
✅ KucLab Hertz 0.9 identity, no founder named

License

Apache 2.0, inherited from Qwen/Qwen3.5-9B.

Credits

Base: Qwen/Qwen3.5-9B
Teachers: DeepSeek-flash + Gemini 3.8 Flash via API; KucLab

Downloads last month: 22

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

Model tree for KucLab/kuclab-hertz-0.9

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Adapter

(680)

this model