Instructions to use google/gemma-4-12B-it-qat-q4_0-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use google/gemma-4-12B-it-qat-q4_0-gguf with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("google/gemma-4-12B-it-qat-q4_0-gguf", dtype="auto")

llama-cpp-python

How to use google/gemma-4-12B-it-qat-q4_0-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="google/gemma-4-12B-it-qat-q4_0-gguf",
	filename="gemma-4-12b-it-qat-q4_0.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use google/gemma-4-12B-it-qat-q4_0-gguf 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 google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0
# Run inference directly in the terminal:
llama cli -hf google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0
# Run inference directly in the terminal:
llama cli -hf google/gemma-4-12B-it-qat-q4_0-gguf:Q4_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 google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0
# Run inference directly in the terminal:
./llama-cli -hf google/gemma-4-12B-it-qat-q4_0-gguf:Q4_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 google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0

Use Docker

docker model run hf.co/google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0

LM Studio
Jan
Ollama
How to use google/gemma-4-12B-it-qat-q4_0-gguf with Ollama:
```
ollama run hf.co/google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0
```

Unsloth Studio

How to use google/gemma-4-12B-it-qat-q4_0-gguf 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 google/gemma-4-12B-it-qat-q4_0-gguf 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 google/gemma-4-12B-it-qat-q4_0-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for google/gemma-4-12B-it-qat-q4_0-gguf to start chatting

How to use google/gemma-4-12B-it-qat-q4_0-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0

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": "google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use google/gemma-4-12B-it-qat-q4_0-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0

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 google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use google/gemma-4-12B-it-qat-q4_0-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0

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 "google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0" \
  --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"

Docker Model Runner
How to use google/gemma-4-12B-it-qat-q4_0-gguf with Docker Model Runner:
```
docker model run hf.co/google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0
```

Lemonade

How to use google/gemma-4-12B-it-qat-q4_0-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0

Run and chat with the model

lemonade run user.gemma-4-12B-it-qat-q4_0-gguf-Q4_0

List all available models

lemonade list

New gemma-4-12B-it-qat Image Didn't work on Ollama version 0.32.0

by ytooyama - opened 1 day ago

Discussion

ytooyama

1 day ago

When you run it, the following error will be displayed:

% ollama run hf.co/google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0
Error: 500 Internal Server Error: llama-server process has terminated: GGML_ASSERT(id_to_token.size() == token_to_id.size()) failed: GGML_ASSERT(id_to_token.size() == token_to_id.size()) failed

% sw_vers
ProductName:            macOS
ProductVersion:         26.5.2
BuildVersion:           25F84
% arch
arm64

tarkasteve

about 21 hours ago

•

edited about 21 hours ago

Same with latest llama.cpp (10054 ac2557cb2):

❯ llama-cli -hf google/gemma-4-12B-it-qat-q4_0-gguf:Q4_0

Loading model... //home/runner/work/llama.cpp/llama.cpp/src/llama-vocab.cpp:2447: GGML_ASSERT(id_to_token.size() == token_to_id.size()) failed
/home/ssmith/services/llama/llama-b10054/libggml-base.so.0(+0x1c79b) [0x7fe78a74f79b]
/home/ssmith/services/llama/llama-b10054/libggml-base.so.0(ggml_print_backtrace+0x21f) [0x7fe78a74fc1f]
/home/ssmith/services/llama/llama-b10054/libggml-base.so.0(ggml_abort+0x152) [0x7fe78a74fdf2]
/home/ssmith/services/llama/llama-b10054/libllama.so.0(_ZN11llama_vocab4impl4loadER18llama_model_loaderRK6LLM_KV+0x44d3) [0x7fe7893ceca3]
/home/ssmith/services/llama/llama-b10054/libllama.so.0(_ZN16llama_model_base10load_vocabER18llama_model_loader+0x44) [0x7fe78938def4]
/home/ssmith/services/llama/llama-b10054/libllama.so.0(+0xc45ef) [0x7fe7892c45ef]
/home/ssmith/services/llama/llama-b10054/libllama.so.0(+0xc5d42) [0x7fe7892c5d42]
/home/ssmith/services/llama/llama-b10054/libllama.so.0(llama_model_load_from_file+0xb6) [0x7fe7892c60a6]
/home/ssmith/services/llama/llama-b10054/libllama-common.so.0(+0x247013) [0x7fe789847013]
/home/ssmith/services/llama/llama-b10054/libllama-common.so.0(+0x2480a2) [0x7fe7898480a2]
/home/ssmith/services/llama/llama-b10054/libllama-common.so.0(_Z17common_fit_paramsPKcP18llama_model_paramsP20llama_context_paramsPfP32llama_model_tensor_buft_overridePmj14ggml_log_level+0x52) [0x7fe78984bb32]
/home/ssmith/services/llama/llama-b10054/libllama-common.so.0(_ZN18common_init_resultC2ER13common_paramsb+0x105) [0x7fe78981da55]
/home/ssmith/services/llama/llama-b10054/libllama-common.so.0(_Z23common_init_from_paramsR13common_paramsb+0x4c) [0x7fe78981f0bc]
/home/ssmith/services/llama/llama-b10054/libllama-server-impl.so(_ZN19server_context_impl10load_modelER13common_params+0xade) [0x7fe789db002e]
/home/ssmith/services/llama/llama-b10054/libllama-server-impl.so(_Z12llama_serverR13common_paramsiPPc+0x39b3) [0x7fe789ce1753]
/home/ssmith/services/llama/llama-b10054/libllama-cli-impl.so(_ZNSt6thread11_State_implINS_8_InvokerISt5tupleIJZN10cli_server5startER13common_paramsEUlvE_EEEEE6_M_runEv+0x15) [0x7fe78afbae75]
/lib/x86_64-linux-gnu/libstdc++.so.6(+0xe1224) [0x7fe78a4e1224]
/lib/x86_64-linux-gnu/libc.so.6(+0x92b7b) [0x7fe78a29eb7b]
/lib/x86_64-linux-gnu/libc.so.6(+0x1107f8) [0x7fe78a31c7f8]
Aborted

lgusm

Google org about 5 hours ago

hey, sorry, we've just fixed the GGUF, it was malformed. everything should work now.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment