Instructions to use jordigonzm/gemma-3-12b-it with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use jordigonzm/gemma-3-12b-it 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 jordigonzm/gemma-3-12b-it:Q8_0
# Run inference directly in the terminal:
llama cli -hf jordigonzm/gemma-3-12b-it:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jordigonzm/gemma-3-12b-it:Q8_0
# Run inference directly in the terminal:
llama cli -hf jordigonzm/gemma-3-12b-it:Q8_0

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 jordigonzm/gemma-3-12b-it:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf jordigonzm/gemma-3-12b-it:Q8_0

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 jordigonzm/gemma-3-12b-it:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jordigonzm/gemma-3-12b-it:Q8_0

Use Docker

docker model run hf.co/jordigonzm/gemma-3-12b-it:Q8_0

LM Studio
Jan
Ollama
How to use jordigonzm/gemma-3-12b-it with Ollama:
```
ollama run hf.co/jordigonzm/gemma-3-12b-it:Q8_0
```

Unsloth Studio

How to use jordigonzm/gemma-3-12b-it 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 jordigonzm/gemma-3-12b-it 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 jordigonzm/gemma-3-12b-it to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for jordigonzm/gemma-3-12b-it to start chatting

Docker Model Runner
How to use jordigonzm/gemma-3-12b-it with Docker Model Runner:
```
docker model run hf.co/jordigonzm/gemma-3-12b-it:Q8_0
```

Lemonade

How to use jordigonzm/gemma-3-12b-it with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jordigonzm/gemma-3-12b-it:Q8_0

Run and chat with the model

lemonade run user.gemma-3-12b-it-Q8_0

List all available models

lemonade list

Atomic Chat

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Run-adjusted to 16GB VRAM

KV cache quantitative and context 8192

./main -m ./gemma-3-12b-it-q8_0.gguf \
  -c 8192 \
  --cache-type-k q8_0 \
  --cache-type-v q8_0 \
  -ngl 999 \
  --batch 96

Key notes:

ngl = nº of layers in VRAM. Upload it as far as it does not give OOM. In 12B it is usually over 28–34 with Q8_0 in 16 GB if the context is large.

If OOM with 8192, go down in this order:

ngl (e.g., 24).
batch (e.g., 64).
c (e.g. 6144 or 4096).

The quantified KV (--cache-type-k/--cache-type-v q8_0) reduces a lot of VRAM for long contexts, at the cost of some performance. It's normal.

Downloads last month: 5

GGUF

Model size

12B params

Architecture

gemma3

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support