Instructions to use jmarceno/Elixir-Gemma-4-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jmarceno/Elixir-Gemma-4-12B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="jmarceno/Elixir-Gemma-4-12B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("jmarceno/Elixir-Gemma-4-12B")
model = AutoModelForMultimodalLM.from_pretrained("jmarceno/Elixir-Gemma-4-12B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jmarceno/Elixir-Gemma-4-12B 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 jmarceno/Elixir-Gemma-4-12B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jmarceno/Elixir-Gemma-4-12B:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jmarceno/Elixir-Gemma-4-12B:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf jmarceno/Elixir-Gemma-4-12B: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 jmarceno/Elixir-Gemma-4-12B:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf jmarceno/Elixir-Gemma-4-12B: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 jmarceno/Elixir-Gemma-4-12B:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jmarceno/Elixir-Gemma-4-12B:Q4_K_M

Use Docker

docker model run hf.co/jmarceno/Elixir-Gemma-4-12B:Q4_K_M

LM Studio
Jan

vLLM

How to use jmarceno/Elixir-Gemma-4-12B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/jmarceno/Elixir-Gemma-4-12B:Q4_K_M

SGLang

How to use jmarceno/Elixir-Gemma-4-12B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "jmarceno/Elixir-Gemma-4-12B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jmarceno/Elixir-Gemma-4-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "jmarceno/Elixir-Gemma-4-12B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "jmarceno/Elixir-Gemma-4-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use jmarceno/Elixir-Gemma-4-12B with Ollama:
```
ollama run hf.co/jmarceno/Elixir-Gemma-4-12B:Q4_K_M
```
Unsloth Desktop

How to use jmarceno/Elixir-Gemma-4-12B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jmarceno/Elixir-Gemma-4-12B: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": "jmarceno/Elixir-Gemma-4-12B:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jmarceno/Elixir-Gemma-4-12B with Docker Model Runner:
```
docker model run hf.co/jmarceno/Elixir-Gemma-4-12B:Q4_K_M
```

Lemonade

How to use jmarceno/Elixir-Gemma-4-12B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jmarceno/Elixir-Gemma-4-12B:Q4_K_M

Run and chat with the model

lemonade run user.Elixir-Gemma-4-12B-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use jmarceno/Elixir-Gemma-4-12B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jmarceno/Elixir-Gemma-4-12B: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 jmarceno/Elixir-Gemma-4-12B:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jmarceno/Elixir-Gemma-4-12B with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jmarceno/Elixir-Gemma-4-12B: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 "jmarceno/Elixir-Gemma-4-12B: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"

Elixir Gemma 4 12B

A Gemma 4 12B model specialized for writing Elixir. It starts from the instruction-tuned QAT checkpoint and is aimed at code that parses, compiles, and passes tests.

The repository contains the merged BF16 weights and a Q4_K_M GGUF for llama.cpp and LM Studio.

Elixir coding results

Scored on a 128-task executable harness. Each task asks for one Elixir module. A pass means the completion parses, compiles, and its tests pass on Elixir 1.20.2 / OTP 29. One completion per task, temperature 0, 16,384-token context, llama.cpp. The base and the fine-tune were both scored as 4-bit GGUF under that same setup.

	Gemma 4 12B QAT	Elixir Gemma 4 12B	Change
Tasks passed	31 / 128	46 / 128	+15
Pass rate	24.2%	35.9%	+11.7 pp
Relative gain			+48%

The fine-tune solves about half again as many Elixir tasks as the base model it was trained from.

Where the gain shows up

Area	Base	Elixir Gemma 4 12B
Standard library	6 / 16	10 / 16
Error handling	8 / 16	11 / 16
OTP	2 / 16	4 / 16
BEAM	1 / 16	3 / 16
Abstractions	1 / 16	3 / 16

Completions are also cleaner: warning-free rate moves from 46.9% to 58.6%, and every completion stays inside a single fenced answer.

Run it

llama.cpp

llama-server -m Elixir-Gemma-4-12B-Q4_K_M.gguf -c 16384 --temp 1.0 --top-k 64 --top-p 0.95

The benchmark file is Elixir-Gemma-4-12B-Q4_K_M.gguf.

Transformers

Needs a Transformers build that knows gemma4_unified.

import torch
from transformers import AutoTokenizer, Gemma4UnifiedForConditionalGeneration

model_id = "jmarceno/Elixir-Gemma-4-12B"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = Gemma4UnifiedForConditionalGeneration.from_pretrained(
    model_id,
    dtype=torch.bfloat16,
    device_map="auto",
)

messages = [
    {
        "role": "user",
        "content": "Write an Elixir module Counter with a GenServer that stores an integer and supports increment and get.",
    }
]
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
output = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(output[0][inputs["input_ids"].shape[-1]:], skip_special_tokens=True))