Instructions to use EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01 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 EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01: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 EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01: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 EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M

Use Docker

docker model run hf.co/EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M

LM Studio
Jan

vLLM

How to use EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M

Ollama
How to use EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01 with Ollama:
```
ollama run hf.co/EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M
```
Unsloth Desktop

How to use EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01: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": "EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01 with Docker Model Runner:
```
docker model run hf.co/EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M
```

Lemonade

How to use EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M

Run and chat with the model

lemonade run user.gemma-4-12b-request-complexity-20260918-01-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01: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 EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01: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 "EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01: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 Request Complexity Scorer — request-complexity-20260918-01

This is an experimental Q4_K_M GGUF export of a fine-tuned google/gemma-4-12B-it model for scoring the complexity of arbitrary user requests from 0 to 100.

The intended output is a single integer:

0–10: noise, empty, trivial acknowledgements
10–30: simple chat or factual requests
30–50: basic reasoning, arithmetic, or single-step transformations
50–70: multi-step practical or coding/debugging requests
70–90: advanced expert reasoning or difficult math
90–100: research-grade, olympiad-level, or highly ambiguous/complex tasks

Artifact

GGUF: training/outputs/model-Q4_K_M.gguf
Quantization: Q4_K_M
SHA-256: 727c993da958113e2e0cdf01d52da59d656751c8b71748e76e89ebb595465de2
Size: 7,381,382,848 bytes
Format magic: GGUF

Training data

The dataset contains 500 supervised chat records:

split	records
train	350
validation	50
verification	100

Sources:

source	records
synthetic	345
MATH-500-derived	145
direct MATH-500	10

The held-out verification split was not used for training.

Training summary

Base model: google/gemma-4-12B-it
Base revision: 707f0a3b8a3c7ad586ed01e27eafbad8a27dd0f7
Steps: 8
Train rows: 350
Validation rows: 50
Baseline validation loss mean: 9.87062
Final validation loss mean: 6.706186
Adapter reload verified: true

Usage

Prompt the model with a user request and ask it to return only an integer from 0 to 100.

Example system instruction:

You score the complexity of the user's request. Return only one integer from 0 to 100. Do not explain.

Example:

User: Prove that there are infinitely many primes of the form 4n+3.
Assistant: 86

Limitations

This is an exploratory fine-tune with a small training set and short training run. The numeric labels are synthetic/derived and should be treated as a calibrated heuristic, not a human-certified measurement.

Held-out verification benchmark

Modal/Ollama inference was run on all 100 held-out verification prompts after public Hugging Face publication. The model was prompted with the direct request and a system instruction to return only one integer complexity score from 0 to 100.

metric	value
scheduled prompts	100
responses	100
valid integer outputs in 0..100	98
parse rate	98.0%
MAE	29.44
RMSE	38.17
Pearson r	0.462
Spearman rho	0.522
exact match among valid outputs	2.0%
within ±5 among valid outputs	14.3%
within ±10 among valid outputs	24.5%
within ±20 among valid outputs	45.9%

The strongest failure mode is MATH-style prompts: the model often answers the math problem instead of scoring its difficulty. This model is therefore not production-ready as a request-complexity scorer; it is useful as a pipeline proof and as evidence for the next dataset/prompting iteration.

Reproducibility artifacts

The repository includes local run evidence files alongside the GGUF:

analysis-summary.json
dataset/manifest.json
training/outputs/export.json
receipts/training-train.json
receipts/training-export.json
scoring/verification-modal-20260918-02/numeric-metrics.json
scoring/verification-modal-20260918-02/predictions.csv
scoring/verification-modal-20260918-02/category-metrics.csv

Generated with finetune-lab run ID request-complexity-20260918-01.

License and attribution

The base model is google/gemma-4-12B-it. The Hugging Face model metadata reports license apache-2.0 with license link https://ai.google.dev/gemma/docs/gemma_4_license. Follow the upstream Gemma terms and attribution requirements when using this derivative artifact.

Downloads last month: 34

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

4-bit

Model tree for EugeneEvstafev/gemma-4-12b-request-complexity-20260918-01

Base model

google/gemma-4-12B

Finetuned

google/gemma-4-12B-it

Quantized

(319)

this model