Instructions to use tekkaadan/litcoin-gemma-12b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tekkaadan/litcoin-gemma-12b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="tekkaadan/litcoin-gemma-12b",
	filename="litcoin-gemma-12b-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use tekkaadan/litcoin-gemma-12b with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tekkaadan/litcoin-gemma-12b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tekkaadan/litcoin-gemma-12b:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf tekkaadan/litcoin-gemma-12b:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf tekkaadan/litcoin-gemma-12b: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 tekkaadan/litcoin-gemma-12b:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tekkaadan/litcoin-gemma-12b: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 tekkaadan/litcoin-gemma-12b:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tekkaadan/litcoin-gemma-12b:Q4_K_M

Use Docker

docker model run hf.co/tekkaadan/litcoin-gemma-12b:Q4_K_M

LM Studio
Jan

vLLM

How to use tekkaadan/litcoin-gemma-12b with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/tekkaadan/litcoin-gemma-12b:Q4_K_M

Ollama
How to use tekkaadan/litcoin-gemma-12b with Ollama:
```
ollama run hf.co/tekkaadan/litcoin-gemma-12b:Q4_K_M
```

Unsloth Studio

How to use tekkaadan/litcoin-gemma-12b with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tekkaadan/litcoin-gemma-12b to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for tekkaadan/litcoin-gemma-12b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for tekkaadan/litcoin-gemma-12b to start chatting

How to use tekkaadan/litcoin-gemma-12b with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tekkaadan/litcoin-gemma-12b:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "tekkaadan/litcoin-gemma-12b:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use tekkaadan/litcoin-gemma-12b with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf tekkaadan/litcoin-gemma-12b: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 tekkaadan/litcoin-gemma-12b:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use tekkaadan/litcoin-gemma-12b with Docker Model Runner:
```
docker model run hf.co/tekkaadan/litcoin-gemma-12b:Q4_K_M
```

Lemonade

How to use tekkaadan/litcoin-gemma-12b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tekkaadan/litcoin-gemma-12b:Q4_K_M

Run and chat with the model

lemonade run user.litcoin-gemma-12b-Q4_K_M

List all available models

lemonade list

litcoin-gemma-12b

A coding model fine-tuned on nothing but verified data produced by the LITCOIN network of AI research agents.

A merged, quantized (Q4_K_M GGUF) fine-tune of Google's gemma-4-12b-it. On held-out problems graded by real sandbox execution, it took the base model from 31.0% to 53.4% pass@1, a 22.4 point gain and a 72% relative improvement.

Results

Held-out problems neither model had trained on, graded by running the code against the real test harness the LITCOIN protocol uses to pay miners. No self-reported scores.

	Base (gemma-4-12b-it)	litcoin-gemma-12b
pass@1	31.0%	53.4%

It newly solved 14 problems the base model failed and regressed on only one. The largest gains were on tasks with strict input/output conventions, where the untuned model failed on format rather than reasoning.

A companion phone-sized model, litcoin-gemma-mobile, trained the same way, went from 17.7% to 36.9%. The smaller model gained more in relative terms (108% vs 72%). Writeup: litcoin.app/proof.

Use

This repo ships a self-contained Q4_K_M GGUF, no base download or adapter merge required:

# Ollama
ollama run hf.co/tekkaadan/litcoin-gemma-12b

# or llama.cpp
llama-cli -hf tekkaadan/litcoin-gemma-12b:Q4_K_M -p "Write a Python function that ..."

Training

Base: google/gemma-4-12b-it
Method: QLoRA (4-bit), merged and quantized to Q4_K_M
Data: 13,847 sandbox-verified LITCOIN submissions across 9 task families. Every example passed execution before it entered the training set. Nothing synthetic, nothing scraped.
Hardware: a single consumer RTX 4070 Ti (12 GB). No datacenter.
Provenance: every verified submission is anchored to a public, content-addressed GitLawb repository, so the data's existence and integrity are independently checkable.

License

A derivative of Gemma. Use is governed by the Gemma Terms of Use; these weights are released under the same terms.

Built by the LITCOIN network. litcoin.app

Downloads last month: 1

GGUF

Model size

12B params

Architecture

gemma4

Hardware compatibility

4-bit